JPS63273901A - Plant controller - Google Patents

Abstract

PURPOSE:To perform the inference at a high speed by excluding a plant monitor function out of a knowledge processing system to reduce the load of a computer of a knowledge system and attaining substantially the exclusive use for an inference function. CONSTITUTION:A plant control part 10 includes a man-machine function part 11 which offers the information via a terminal 36, an information collecting/ processing part 12 which collects and processes the information given from a subject plant 34 via a process input/output device 32, a plant data base 13, a plant data base production part 14 which arranges and edits the plant information, and a controller SCC15. A monitor function part 17 stores the signs of plant abnormality, the knowledge of the state decision and the procedure in the form of a procedure program and detects the abnormality. A knowledge processing system 20 includes an inference function part 22 which infers the countermeasures via a knowledge base 21 and a man-machine function part 23 which offers the result of inference and the related information via a terminal 38. In such a constitution, a monitor function is omitted out of the system 20 and the number of inference rules are decreased. Then the computer load of the system 20 is reduced and the processing time is shortened.

Description

[Detailed Description of the Invention] (Industrial Application Field) The present invention relates to a plant control device, and in particular, realizes more intelligent functions such as optimal plant control, abnormality control, predictive control, and plant diagnosis. This invention relates to a plant control device suitable for.

(Prior art) It is possible to infer or identify the causes of abnormalities in various plants by using a knowledge base obtained by accumulating, classifying, and organizing the knowledge and experience of experts in the field, for example, as described in Japanese Patent Application Laid-Open No. 60
It is disclosed in Japanese Patent No.-14303. Here, a group of cause/effect rules, a group of result/cause rules, and a group of cause estimation rules are prepared as a knowledge base, and when an abnormality symptom is detected in the collected plant information, the above rule group is used. Based on this, the causes of abnormalities in various plants, etc. are inferred or identified.

A plant control computer that uses the knowledge base described above to perform control using a conventional procedural programming language, equipment diagnosis, abnormality detection, operator guidance (instructions to the operator) in the event of an abnormality, and/or automatic control, It is conceivable to organically combine the knowledge processing system with a knowledge processing system having an inference function for carrying out protective operations, and to quickly and accurately control a plant or the like in the event of an abnormality.

As described above, the knowledge base is a software representation of procedures and techniques for knowledge processing based on the knowledge and empirical know-how of experts in the field.

In other words, this knowledge base is based on the knowledge of abnormality detection and abnormality treatment methods acquired through the past experience of the expert.

They are organized in the format of then... and registered as rules, and the data required by the rules are also registered in the form of frames.

The inference function infers causes and countermeasures for abnormal symptoms based on the above-mentioned knowledge base.

The inference results can be used in various ways, such as being used as a CRT output to an operator, printed out to a typewriter, etc., or transferred as data to another system. In any case, the results obtained by the inference function can be handled as information by other systems or by humans.

When a knowledge processing system equipped with such a knowledge base and inference function is used for online control, the following configuration or method can be considered.

That is, data obtained from the process control device of the plant or the control device of another system is imported into the knowledge processing system, and abnormalities or signs of abnormality in the plant are detected using the knowledge described by the rules in the knowledge base.

If an abnormality or abnormal symptom is detected, an inference function is activated to perform inference on how to deal with the abnormality or abnormal symptom based on the rules and frames in the knowledge base.

The conclusions obtained by the inference function are displayed as instructions for the operator or used as they are as commands for online automatic control.

(Problems to be Solved by the Invention) In the above-mentioned case, the knowledge processing system will be responsible for both the function of detecting or monitoring abnormalities or signs of abnormality in the plant based on plant information and the inferring function.

By the way, abnormality monitoring of a plant must be carried out continuously, and countermeasures for the occurrence of abnormalities or abnormal symptoms should be deduced in the shortest possible time.

On the other hand, since there is a limit to the calculation speed and therefore processing power of the computer in the knowledge processing system, there is also a limit to the speed of the inference function. Furthermore, even if a plant abnormality or abnormality symptom is detected, the inference function may not be activated immediately.

For this reason, when the rate of state change in the plant is large,
(Protection) measures based on the results of the inference function may be delayed.

In particular, if multiple abnormalities or abnormal symptoms are detected and inference functions for them are activated in parallel, the time required to reach a conclusion will naturally become longer, and the above-mentioned fear will become even greater.

An object of the present invention is to enable inference by directing the processing power of the computer of the knowledge processing system to the inference function as much as possible when the inference function is activated in response to the detection of an abnormality or abnormality symptom in a plant. The object of the present invention is to provide a plant control device that can perform operations at high speed in a short period of time.

(Means for solving the problem) The above purpose is to remove the plant monitoring function from the knowledge processing system, reduce the burden on the computer of the knowledge processing system, and practically dedicate the inference function. This is achieved by

In this case, the monitoring function can be performed by a plant control computer that collects and stores data from the target plant, and performs normal control.

(Function) By writing the monitoring function for detecting abnormalities or signs of abnormality from the plant in a conventional procedural programming language and adding it to the plant control system, its processing performance, that is, real-time performance, is ensured, so the plant If it is determined that an abnormality or an abnormal symptom has occurred, the computer of the knowledge processing system equipped with an inference function can be activated immediately.

On the other hand, in a knowledge processing system, since the monitoring function described in the form of rules is eliminated, the total number of rules to be considered when inferring processing for plant abnormalities is reduced.

Therefore, the computer load on the knowledge processing system for inference is reduced, and the processing time of the knowledge processing system is shortened.

Not only that, the knowledge processing system no longer needs to execute the monitoring function, which also helps reduce the load on the computer, so the time taken to process the inference function of the knowledge processing system is significantly reduced. be done.

(Example) The present invention will be described in detail below with reference to the drawings. A schematic block diagram of one embodiment of the present invention is shown in FIG.

The plant control device of the present invention includes a plant control section 10 using conventional procedures and a knowledge processing system section 20.

The plant control unit 10 according to the conventional procedure is normally operated by the terminal 3
6, a data collection unit/processing unit 12 that collects information from the target plant 34 via the process input/output device 32, Plant data base for storing data13. It has a plant data base creation section 14 that organizes and edits the data stored in the plant data base 13, and an SCC (Supervisory Computer Control) that controls each of these sections.

Furthermore, the plant control section 10 includes a monitoring function section 17.

The monitoring function unit 17 rewrites the knowledge of signs that abnormalities may occur in the plant, and the knowledge and procedures for determining abnormal conditions into a procedural program based on the knowledge of experts in the target plant and know-how obtained through experience. Based on the plant data obtained by the data collection unit/processing unit 12, the occurrence of abnormality or abnormality symptoms in the plant is detected.

On the other hand, the knowledge processing system unit 20 includes a knowledge base 21 that stores knowledge, that is, the aforementioned rules and frames, an inference function unit 22 that uses the knowledge to infer countermeasures or means for avoiding or recovering from plant abnormalities, and an inference result. It also includes a man-machine function section 23 that provides information related thereto to the user via the high-performance terminal 38.

Next, the functions and operations of each part will be explained in detail while following the flow of information.

Information on the target plant 34 is converted into data by the process human output device 32, and is stored and managed in the data collection unit/processing unit 12. Specifically, analog information and digital information of the plant are digitized within the process input/output device 32 and temporarily managed within the data collection/processing section 12.

Some of the information is provided to the user by the man-machine function section 11. There are various forms of provision in this case, but
Typically, the information is displayed on a CRT placed in the terminal 36 or printed out using a typewriter or the like.

Also, some information is stored in the plant data base 13. The stored data is processed by the plant data base creation unit 14 and stored in an auxiliary memory (fixed disk or the like) as historical data or the like.

Furthermore, some of the information is used as plant control data and is output to the process input/output device w132 via the controller of the 5CC 15 to control the target plant 34.

Next, the monitoring function section 17 adds the plant data (frames) collected in the data collection/processing section 12 to the knowledge and procedures (rules) for determining the occurrence of plant abnormalities or abnormal symptoms stored therein in advance. Apply this to detect the occurrence of plant abnormalities or abnormal symptoms.

For example, if the knowledge indicating the sign of an abnormality is "If the NO31 pump frequency is 360 Orpm or more, there is a high possibility that it will have an adverse effect on the plant", No.
The latest information regarding the rotation speed of one pump is periodically read from a management table (not shown) in the data collection unit/processing unit 12, and it is checked whether the data is 360 Orpm or more.

If the rotation speed of the NO.1 pump is 3,600 rpm or more for a longer period than a predetermined (regulated) time, the monitoring function unit 17 sends a detection signal of "rotation speed abnormality", that is, an event occurs. Issue.

The event informing that "rNo. 1 pump rotational speed is abnormal" is supplied to the inference function section 22 of the knowledge processing system section 20. In response to this event, the inference function unit 22 selects knowledge (rules) regarding the number of rotations of the No. 1 pump and performs inference regarding them.

The results obtained from this inference can be used as operation number guidance for operators in the man-machine function section 2.
3 on the high-performance terminal 38 (CRT display or typewriter printing), or is supplied to the data collection/processing unit 12 as a control output to the target plant 34.

In the above specific example, the results of the inference are rNo, stop operation of one pump, and no, respond with two pumps at the same time.

As a result, the plant control unit 10 is instructed to output an output signal to stop the operation of the N011 pump in accordance with the method of writing the rule, and at the same time the output signal is NO.

The output of an output signal for starting the two pumps is instructed.

Furthermore, depending on the method of writing rules, it is possible to make the above-mentioned inference result a cadence for the operator, and it is also possible to do both at the same time.

The above-mentioned monitoring function is realized by creating a monitoring program for each facility and each device, and starting and executing each program at predetermined intervals.

Then, as described above, when an abnormality or an abnormality symptom is detected in any of the facilities or devices, the knowledge processing system is requested to perform inference for each facility or device.

For this reason, multiple inference execution requests to the inference function unit 22 may occur at the same time, but the inference function unit 22 can also infer complex detection processing by comprehensively viewing these requests. .

For this purpose, a rule written in the If, then... format that includes a combination of abnormality or abnormality symptoms of each facility or device for the above-mentioned coincidence detection is required in advance. It goes without saying that you must be prepared.

FIG. 2 is a flowchart showing the flow of monitoring, inference, and control based on the inference results, taking as an example the knowledge of abnormal symptoms that may occur in the pump.

The monitoring program in the monitoring function section 17 is activated periodically, for example, every second, and the latest data on the number of revolutions of the No. 1 pump is sent to the management table 121 in the data collection/processing section 12.
(step 511) and check whether the value is 3600 or more (step 512).

If the number is less than 3600, the program ends and waits for the next startup.

However, if it is 3600 or more, there is a great possibility that it will have a negative impact on the plant, so the knowledge processing system section 20
An event called "rotation speed abnormality" is issued to the inference function unit 22 of the pump, and an inference regarding the rotation speed abnormality of the pump is requested (step 513).

The inference function unit 22 starts the knowledge processing program in response to this request.

The knowledge processing program is a knowledge base (rules and frames) 21 regarding pumps stored in a knowledge base 21.
A and make inferences about the pump (step 5
21) Output the inference results regarding the abnormality handling work or countermeasures for the pump (step 522).

The inference results are sent to the man-machine function section 23 in order to be displayed on the CRT of the high-performance terminal 38 as work instructions to the operator.
Or, the data collection/processing unit 12 of the plant control unit 10 is sent an instruction to automatically process the abnormality of the pump (for example, stopping the pump No. 1 and stopping the pump No. 2).
This is sent as a pump start instruction).

The data collection/processing unit 12 of the plant control unit 10 starts a plant control program for causing the process human output device 32 to output a signal for abnormality processing via the 5CC 15 based on instructions based on the conclusion.

This allows abnormality processing work (
In this example, N011 pump stop) is performed (step 531). The fact that the pump was stopped means that
Confirmed by the monitoring program, the knowledge processing and plant control according to the invention ends.

In addition, although the case where the present invention is applied to abnormal control of a plant has been described above, it is natural that similar knowledge processing and plant control can be applied only to optimal control, plant diagnosis, etc.

(Effects of the Invention) As is clear from the explanation below, according to the present invention, the following effects are achieved.

(1) Since the plant monitoring function does not impose a load on the computer of the knowledge processing system, the inference function can be performed at high speed, and the knowledge processing system can be applied even to plants whose status changes quickly, and when abnormalities or It is not only possible to early determine (protective) countermeasures when abnormal symptoms occur and notify them, but also to easily replace them with automatic processing.

('2J Since the monitoring function is separated from the inference function, the monitoring function itself can be made faster and faster.

(3) The combination of (1) and (2) above facilitates high-speed plant control.

(4) In the field of control, tasks that traditionally involve human judgment can be replaced with machine processing.

[Brief explanation of the drawing]

FIG. 1 is a functional block diagram of one embodiment of the present invention. FIG. 2 is a control flowchart showing an example of the operation. 10... Plant control unit, 11.23... Man-machine function unit, 12... Data collection/processing unit, 13...
-Plan database, 14...Plant data base creation unit, 15...SCC, 17...Monitoring function unit, 20...Knowledge processing system unit, 21...Knowledge base, 22... Inference function unit, 32... Process human output device, 34... Target plant, 36... Normal terminal, 38... High performance terminal

Claims (7)

[Claims] (1) A plant control device comprising a plant control section and a knowledge processing system section, wherein the plant control section includes a data collection/processing section that collects and processes data obtained from a target plant, and the collected data. a monitoring function unit that detects a state in the target plant based on a knowledge base that stores knowledge regarding the target plant, and a knowledge processing unit that detects the state of the target plant based on a request from the monitoring function unit. A plant control system comprising: an inference function section that infers a countermeasure against the detected state of the target plant using knowledge in a base, and outputs the inference result to at least one of a terminal and a plant control section. Device. (2) The knowledge stored in the knowledge base is If..., t
2. The plant control device according to claim 1, comprising a rule written in the format of hen... and a frame for storing data applied to the rule. (3) The plant control device according to claim 1 or 2, wherein the inference result is displayed on a terminal via a man-machine function section. (4) The plant control device according to claim 1 or 2, wherein the inference result is supplied to the plant control section and used to automatically control the target plant. (5) The knowledge stored in the knowledge base is a countermeasure according to the detected state of the target plant, which is obtained based on specialized knowledge and experience in the field. The plant control device according to any one of items 1 to 4. (6) The plant control device according to claim 1, wherein the inference function section is operated by a computer separate from the computer of the monitoring function section. (7) The plant control device according to claim 1, wherein the detected state of the target plant is an abnormality or a symptom of the abnormality, and the knowledge is a countermeasure to eliminate the abnormality.