JPH079010B2 - Blast furnace operation management system - Google Patents

Description

The present invention relates to a blast furnace operation management system using knowledge engineering.

[Conventional technology]

Blast furnace operation consists of a large number of operation factors that are mutually related, and it is difficult to visually monitor the inside of the furnace directly from the equipment conditions. In order to achieve this, it is necessary to comprehensively judge the information from the sensors installed in the blast furnace and control it appropriately. For this reason, the experience and knowledge of operators are still important for the daily operation management of blast furnaces.

Since the knowledge engineering system can take in such human know-how into a computer and process it, there is a problem in Japanese Patent Laid-Open No. 62-2707.
The introduction of a knowledge engineering system for blast furnace operation management as shown in JP-A-08 and JP-A-62-270712 is being promoted. By systematizing operation management, problems such as oversight of information and erroneous judgments will be eliminated, and operation management will be optimized and standardized.

[Problems to be Solved by the Invention]

In the blast furnace operating method applying the conventional knowledge engineering disclosed in JP-A-62-270708 and JP-A-62-270712, as a result obtained by inference, blow-through, slip prediction, furnace heat A knowledge base is established for partial items of phenomena in the blast furnace, such as situation determination, and inferences are made independently of each other.

However, in-furnace phenomena such as aeration, load drop, furnace heat, etc. occurred as mutually related processes in one blast furnace process. As a blast furnace operation management system, these individual phenomena are comprehensively evaluated. It is necessary to judge and link to action. For this purpose, a large-capacity knowledge base from the huge amount of information of the blast furnace to the final decision is required.

Furthermore, as another condition necessary for the operation management system of the blast furnace, it is necessary to be able to immediately grasp the change in the internal condition of the blast furnace, which is a continuous reactor, and determine the countermeasure. That is,
It is necessary to minimize the cycle of reasoning that is executed regularly. However, the inference cycle is inevitably limited by the processing time such as preparation of inference data and execution of inference, and inference execution by a large-capacity knowledge base that requires a large amount of data processing is a single process. Since the time is long, the reasoning cycle cannot be shortened. Therefore, if a large-capacity knowledge base is used to comprehensively judge the in-furnace condition of the blast furnace, the judgment is not quick. On the other hand, in order to shorten the inference cycle, it is necessary to make the knowledge base small in capacity, and there is a problem that the accuracy of judgment is lacking.

Therefore, the present invention has been made to solve such problems, and aims to obtain a blast furnace operation management system capable of quick and comprehensive in-reactor situation and action determination by using knowledge engineering. To do.

[Means for Solving the Problems]

The blast furnace operation management system according to the present invention infers the in-furnace situation of the blast furnace by using knowledge engineering, and in the method of operating based on this result, as a pre-stage of the knowledge engineering system while performing inference at a constant cycle, It is characterized in that it is provided with a detecting means for detecting a change in one or more management items, which temporarily activates inference by the knowledge engineering system even when the measured values of the management items deviate from the management values.

[Action]

The means of detecting changes in the control items are the rapidly changing temperature of the gas in the furnace and the hot metal temperature and components that do not generate data periodically. Start to Lee. On the other hand, slow changes in the blast furnace are dealt with by executing inferences at regular intervals.

〔Example〕

Embodiments of the present invention will be described below with reference to the drawings. First
FIG. 1 is a schematic diagram of the configuration of a blast furnace operation management system according to an embodiment of the present invention, in which 1 is a blast furnace, 2 is a detection means for catching a change in a management item of the blast furnace, and initiating inference by a knowledge engineering system, 3 is knowledge. An engineering computer, 4 is a database file in which information from the blast furnace 1 is stored in a state in which it can be used for inference execution, 5 is a knowledge base file in which various knowledge bases are registered in an inference executable state, 6 is a database file 4 An inference engine that executes inference based on the data prepared inside and the knowledge base registered in the knowledge base file 5, and 7 controls the execution of inference according to conditions such as preset inference cycle and external start conditions. Reference numeral 8 denotes a terminal for performing execution management and outputting inference results.

In the database file 4, periodic data such as air flow rate, ventilation resistance index, furnace top temperature, etc. sent from the process computer, non-constant periodic data such as hot metal temperature, hot metal component, and tuyere coke manually input by the operator Data such as the turning situation is sequentially updated and stored as each data is generated. In the knowledge base file 5, a knowledge base constructed by a general method in knowledge engineering, which comprehensively judges the situation inside the blast furnace and derives an appropriate action, is registered.

FIG. 2 is a functional explanatory diagram of the detection means 2 of FIG. In the embodiment of the present invention, the blast pressure, the hot metal temperature, the furnace top temperature, and the charging depth are adopted as the control items 9 from the blast furnace 1,
Set the control value of each control item in advance. The presence or absence of deviation 10 from the management value of these control item actual measurement values is detected, and when there is deviation, a signal of an inference start command 11 is sent to the knowledge engineering computer 3. It is preferable that the detection means 2 is configured by providing an instrumentation microcomputer or a process control process computer with a function.

FIG. 3 is an explanatory diagram of inference based on the knowledge base of the present invention. Blast furnace operation information 12 includes information on gas distribution such as radial gas temperature and composition distribution by upper sonde, gas distribution information such as radial gas temperature distribution by furnace top sonde, hot metal temperature, heat level related information such as Si in pig iron, ventilation resistance index, etc. Ventilation level related information, furnace upper part temperature related information such as shaft upper water-cooled metal temperature, furnace lower part temperature related information such as furnace abdomen brick temperature, load drop related information such as abnormal drop frequency, tuyere tip coke turning status, etc. Tumor condition related information is categorized, and based on the classified information, the gas distribution condition, heat level condition, ventilation level condition, upper furnace temperature condition, lower furnace temperature condition, load descent condition, tuyere condition are inferred. Perform intermediate determination 13. Based on the intermediate judgment 13 for each of the classifications, the in-reactor situation comprehensive judgment 14 is performed, and the optimum action instruction 15 is output.

FIG. 4 is an explanatory diagram of an operation example of the system of the present invention.
In the embodiment shown in the figure, the regular inference is preset as a 30-minute cycle. In the figure, the black circles in the inference execution indicate the execution of the periodic inference, and the white circles indicate the inference by the inference start command from the detection means 2. Was executed.
Moreover, the furnace top temperature is adopted as the management item 9 of the blast furnace.
At 60 minutes in the figure, the operation status is determined to be unstable due to the inference execution at regular intervals, and an action instruction is issued. 80
In the minute, the fact that the actual measurement value of the furnace top temperature is out of the control range is detected by the detection means 2, and the inference start command is sent and the inference is executed, but it is determined that the operation state is in a stable state. However, action instructions have not been reached.
Further, in 140 minutes, as in 80 minutes, the fact that the measured value of the furnace top temperature is out of the control range is detected by the detection means 2, and as a result of starting the inference, it is determined that the operation status is unstable, and an action instruction is given. Has reached.

〔The invention's effect〕

The present invention, as described above, activates the inference by the knowledge engineering system for comprehensively judging the in-furnace situation and deriving an action even when the change in the management item of the blast furnace is caught, thereby rapidly changing the in-reactor situation. It is possible to catch, determine the appropriate situation inside the furnace and take action.

[Brief description of drawings]

 FIG. 1 is a schematic diagram of the system configuration of the present invention, FIG. 2 is a functional explanatory diagram of the detection means of the present invention, FIG. 3 is an explanatory diagram of inference by a knowledge base of the present invention, and FIG. It is explanatory drawing of the system operation | movement of invention.

 ─────────────────────────────────────────────────── ─── Continuation of the front page (72) Inventor Hiroshi Oda 1 Kimitsu, Kimitsu-shi, Chiba Nippon Steel Corp. Kimitsu Works (56) Reference JP 62-270708 (JP, A) JP Sho 62-270712 (JP, A)

Claims (1)

[Claims] 1. A method of inferring the in-furnace condition of a blast furnace by using knowledge engineering, and performing an operation based on this result, the inference is performed at regular intervals, and the control items are actually measured as a pre-stage of the knowledge engineering system. A blast furnace operation management system comprising means for detecting a change in one or more control items so that reasoning by a knowledge engineering system is temporarily activated even when the value deviates from the control value.