JPH01145263A - Instruction assisting system - Google Patents

Abstract

PURPOSE:To prevent the erroneous processing and delay of disposition by automatically recognizing the necessary method of disposition and the contents of anomaly from an abnormal state in case of the anomaly of an object system and environmental system and displaying the contents for an instructor from a central instruction room. CONSTITUTION:An information base 1 memorizes the supposition of the judgement and disposition for the environmental system information such as the information related to an object system which an instructor possesses, the environment such as weather conditions, and other designation, according to the rule in the conditional terms which consist of a premise part and execution part. An information file 2 which receives and memorizes the information of the object system and environmental system is installed. When an abnormal state in which the necessary disposition is issued by the instructor, an inference device 4 successively generates the method of disposition and the contents of anomaly according to the rule of the information base, on the basis of the information inputted through the information file 2 and a dialogue device 3 with instructor, which displays the necessary instruction information.

Description

[Detailed description of the invention] [Object of the invention] (Industrial application field) This invention is applicable to driving commands, train commands,
This invention relates to a command support system for supporting command and educational affairs in central commands such as electric power commands.

(Prior Art) Conventionally, automation of central commands such as driving commands, train commands, and power commands in a central control room has been performed by a centralized monitoring υJllll system. The purpose of this conventional centralized monitoring and control system is to centrally monitor status data such as train position, course, switchgear status at substations, and various failures, and to control course direction, switchgear status, etc. It is something.

From a dispatcher's point of view, this conventional centralized monitoring and control system:
It is a device that can recognize the status of the target system from the displayed information and inputs necessary control commands. Therefore, how to recognize the state of the target system,
It is left to the discretion of the dispatcher to decide what kind of treatment to order and what kind of treatment to order in response to various surrounding situations.

(Problem to be Solved by the Invention) However, in commands using such conventional command support systems, the criteria for judgment imposed on the dispatcher described above are not described as basic contents in the command work manual etc. However, the numbers are based on the knowledge gained from the experience of the dispatcher, and after examining various conditions,
Judgments are often made through trial and error, and it has been difficult to express this judgment standard as an algorithm and automatically obtain the necessary commands.

Therefore, when commands are issued by the conventional centralized monitoring and control system, there are problems such as erroneous treatment due to erroneous judgment by the dispatcher, or delays in appropriate processing due to excessive time required for judgment.

This invention was made to solve these conventional problems, and when there is an abnormality in the target system, environment, or surrounding systems in the central control room, the necessary treatment method and abnormality can be determined based on the abnormal state. The content can be automatically determined and shown to the dispatcher, preventing the dispatcher's judgment, errors in treatment, and delays in treatment, and allowing appropriate measures to be taken promptly. The purpose is to provide a command support system.

[Structure of the Invention] (Means for Solving Problems) As shown in FIG. A knowledge base 1 that stores the judgment and treatment process for information in the surrounding system, such as commands, using rules in the form of conditional statements consisting of a prerequisite part and an execution part; an information file 2 for inputting and storing information; a dispatcher dialogue device 3 for displaying information such as treatment methods and abnormalities to the dispatcher and inputting treatment results from the dispatcher; and the information file. 2 and an inference device 4 that sequentially derives processing methods and abnormality contents according to the rules of the knowledge base 1 from the information inputted through the dispatcher dialogue device 3 and displays necessary command information on the dispatcher dialogue device. It is equipped with the following.

(Function) In the command support system of the present invention, in the event that an abnormal condition that requires action by the dispatcher occurs, inferences are made based on changes in information in the information file 2 or input from the dispatcher dialogue device 3. The device 3 checks whether the answer condition of the prerequisite part of the rule of knowledge base 1 is satisfied, and if it is satisfied, the execution part is assumed to be satisfied, and if the execution part is one of the conditions of the prerequisite part, then Assuming that the execution part is established, by repeatedly performing this demonstration, we finally find an execution part that is not the prerequisite part, and display information on this final execution part on the dispatcher dialogue device 3. This will notify the dispatcher so that appropriate measures can be taken.

(Example) Hereinafter, embodiments of the present invention will be explained in detail based on the drawings.

FIG. 2 shows an embodiment of the present invention, including an input/output device 11 which is a dispatcher dialogue device, a man-machine interface processing section 12, a knowledge base 13, an inference device 14, a working memory 15, and a target/surroundings information file. 16, an online data processing section 17, and another system interface section 18.

The input/output device 11 is composed of a display, a keyboard, a voice response device, etc. The input/output device 11 is configured by a display, a keyboard, a voice response device, etc., and the man-machine interface processing unit 12 processes the input/output device 11 to inform the dispatcher of treatment methods, the target system 19, the environment, surrounding systems, etc. It displays and outputs the abnormal states of the system 20, the processes by which they were derived, etc., and also inputs information, operation requests, etc. from the dispatcher.

The knowledge base 13 stores knowledge of judgments and treatment processes in commands in the form of rules with respect to information obtained as a result of treatment of other systems 20 such as the target system 19, the environment, surrounding systems, and commands. This rule is IF~,T)-
It is written in the form IEN~, with IF~ as the prerequisite and TH
EN~ is called an execution unit.

FIG. 3 shows an example of this rule, and this rule configuration is based on AND,
It is constructed by logical operations such as OR. Therefore, if the logic of the premise part 40 is established, the execution part derives the abnormal state and the treatment method 41. Furthermore, conditions 1 to K of the result information obtained by implementing the treatment method 41 are set as additional conditions 42, the previous abnormal state and its handling method 41, and these additional conditions 42 are set as a prerequisite part 43 similar to the above, and these As an execution part for the prerequisite part 43, the next abnormal state and treatment method 44 are derived.

Furthermore, by repeating this rule, the final abnormal state and treatment method 45, which is the execution part that is not the premise part, are finally derived. This final abnormal state and treatment method 45 will be referred to as a hypothesis hereinafter.

The inference device 14 is a part that repeatedly confirms the establishment of each condition of the rule shown in FIG. 3 stored in the knowledge base 13 and derives a hypothesis.

The working memory 15 is a part that sequentially stores the states of the inference device 14 during the derivation process.

The target and surrounding information file 16 contains various information representing the state of the target system 19 that is input through the processing of the online data processing section 17 and information about the other system 20 that is input through the processing of the other system interface section 18. Stores various information.

The operation of the command support system having the above configuration will be explained next.

If any abnormality occurs in the target system 19 or other systems 20 such as the environment or surrounding systems, the corresponding information in the target or surrounding files 16 will change via the online data processing unit 17 or other system interface unit 18, or the information will be changed directly. Abnormality information is input from a dispatcher via the input/output device 11.

The operation of deriving a hypothesis using this input information is as follows.

With reference to FIGS. 3, 4, and 5, the inference device 14
In step 51), it is checked whether the information changed or input in step 50 satisfies any of the conditions of the target information or surrounding information of the prerequisite part 40 of the rule in the knowledge base 13 of FIG. If there is a condition that holds true, it is assumed by forward inference that the premise including the condition holds true, and the execution part 41 is derived from the IF-THEN rule (step 52).

If this execution part 41 is also a condition of the premise part 43, it is assumed that the whole premise part 43 is satisfied, the next execution part 44 is derived in the same way, and the following is repeated. IFT) (Applying the EN rule, it is assumed that the corresponding hypothesis 45 finally holds true.

Note that there may be a plurality of hypotheses 45 (step 52).

Next, whether or not the obtained hypothesis 45 satisfies all the conditions is confirmed by backward inference, starting from the lowest premise, which was assumed to have been established in step 52 (step 53). That is, as shown in the detailed flow in FIG. 5, first check whether all the conditions for information on the target system 19 and information on other systems 20 are satisfied (step 60), and if the prerequisites are satisfied, then The input/output device 11 displays abnormal conditions and how to deal with them.
The information is displayed to the dispatcher and instructions for the next action are given (step 61).

If this next action is not a hypothesis, the dispatcher takes the necessary action according to the indicated countermeasure, and the information obtained as a result is sent to the input/output device 11, online data processing section 17, or other system interface section 18. It is checked whether the conditions of the result information, which is input into the target and surrounding information file 16 and is a prerequisite for the next treatment, are correct (step 62).

The confirmed information is then stored in the working memory 15 (step 63).

This confirmation is carried out in a step-by-step manner, measuring toward the higher rank. When all conditions are satisfied, the hypothesis is established (step 64), and the process returns to step 53 in Fig. 4 and the same procedure as above is performed for another hypothesis. Do not repeat the operation (step 54). When the backward IW wheel action described above is completed for all hypotheses, the final abnormal state and treatment method are displayed to the dispatcher through the input/output device 11 (step 55).

If the backward inference in step 62 shown in FIG. 5 does not hold, it is assumed that the hypothesis does not hold, and the process returns to step 53 shown in FIG. 4, and backward inference is performed again on the next hypothesis. If a hypothesis that holds true is not found, the input/output device 11 displays a message indicating that the cause of the failure and how to deal with it are unknown.
As an example of the judgment effect of the above-mentioned IFT)-IEN rule, which will be given to the dispatcher via the (step 56), FIG. 6 shows the rule for the power command.

When an accident occurs in the feeder line that supplies power to a vehicle, the dispatcher determines the first action based on information such as the relay operating status and fault point orientation value, and then makes the next decision based on the information on the results of that action. are being treated.

FIG. 6 shows a case where a fault current flows through a feeder line due to a fault in a train. Information 71 indicating that the breaker is operating and information 72 indicating that the heavy duty circuit breaker has tripped and failed to reclose are stored in the target and surrounding information file 16 via the online data processing unit 17. Then, based on this input information, the inference device 14 performs forward inference by checking whether the corresponding conditions of the prerequisite part of this rule hold, and issues a command to "prevent train failure" as one of the hypotheses. 73 is derived as a candidate.

At this time, the operation information 70 of the above-mentioned feeder line protection relay 1,
All hypotheses of rules whose prerequisites include the operation information 71 of the feeder line protection relay 2 and the information 72 of the heavy duty circuit breaker trip and failure to reopen are derived as candidates and stored in the working memory 15. become.

Next, these candidate hypotheses are sequentially confirmed by backward inference. The priority order of this backward reasoning can be set as appropriate, such as in the order of urgency, the order of possibility, or the order of importance.

The process of confirming the train failure hypothesis 73 is performed by performing backward inference and confirming whether the unconfirmed condition is met or not. In other words, information 74 with failure point target value displayed;
Check whether the information 75 indicating that a train is present at the failure point location has been input, the stored contents of the surrounding information file 16, the input information given by the dispatcher via the input/output device 11, or when other hypotheses have already been confirmed. This information is confirmed based on the contents stored in the working memory 15.

If these conditions are satisfied, the entire premise is established, and the command information for the premise part 81 as the execution part is ``There is a train failure, so lower the pantograph and perform a trial electric charge.'' 76 is output, and the dispatcher looks at this command displayed on the input/output device 11 and performs the necessary test power.

After this, the result of the trial electricity is sent to the dispatcher via the input/output device 11, or if the information is input to the target/surroundings information file 16 online, the result is confirmed in the target/surroundings information file 16. , if the information 77 of "trial run success" also holds true, this prerequisite part 82 is satisfied, it is confirmed that a train failure has occurred, and the execution part 83 executes the hypothesis [Treatment of train failure will be taken. ” condition 73 is satisfied, the information is displayed to the dispatcher via the input/output device 11.

At this time, the display by the input/output device 11 outputs detailed treatment methods for dealing with train failures, so that even inexperienced dispatchers can take appropriate measures.

In this way, in this example, the target system 19
This allows the dispatcher to accurately display and instruct the dispatcher on how to make judgments and take action based on the situation of other systems 20, such as the system, environment, and surrounding systems. Even in difficult situations, it will be possible to take the necessary response measures appropriately and quickly without confusion.

Note that the present invention is not limited to the above-described embodiments, and for example, information may be directly exchanged between the man-machine interface processing unit 12 and the object, surrounding information file 16, and online data processing unit 17. By providing these with a monitoring function and a control function, a centralized monitoring and control system having both a command decision support function and a centralized monitoring and control function can be obtained.

In addition, if the online data processing unit 17 and other system interface unit 18 automatically perform the processing in the backward inference and the confirmation of the results in the embodiment in addition to the centralized monitoring control function, the confirmation processing that can be automated can be commanded. This will enable automation of the decision-making and processing tasks performed by staff.

[Effects of the Invention] As described above, according to the present invention, by using a knowledge base and an inference device, when an abnormality occurs, it is possible to automatically find out the cause and necessary countermeasures, thereby reducing the judgment work of dispatchers. It is possible to reduce the burden, and even inexperienced dispatchers can take appropriate response measures.

[Brief explanation of the drawing]

FIG. 1 is a block diagram of an embodiment of the present invention, FIG. 2 is a block diagram of a more detailed embodiment of the invention, FIG. 3 is an explanatory diagram explaining the IF-THEN rule of the above embodiment, and FIG. The figure is a flowchart explaining the operation of the above embodiment, FIG. 5 is a flowchart explaining the backward reasoning operation in the above embodiment, and FIG. 6 is an example of the IF-THEN rule for the power command in the above embodiment. It is an explanatory diagram. 11... Input/output device 12... Man-machine interface processing unit'
13...Knowledge base 14...Inference device 15.
...Working memory 16...Target, surrounding information file 17...Online data processing section 18...Other system interface section a.

Claims (2)

[Claims] (1) A conditional statement consisting of a prerequisite part and an execution part that describes the process of judgment and action regarding the information on the status of the target system held by the dispatcher, the environment such as weather, and information on surrounding systems such as other commands. A knowledge base that is stored according to rules in the form of A dispatcher dialogue device that inputs the results of actions etc. from the dispatcher; and a dispatcher dialogue device that sequentially derives treatment methods and abnormality contents according to the rules of the knowledge base based on the information input through the information file and the dispatcher dialogue device. , and an inference device that causes the dispatcher dialogue device to display necessary command information. (2) The inference device has a function of automatically outputting a necessary control command for the target system according to the content of the derived processing method. command support system.