JPH0726127B2 - Blast furnace furnace automatic heat control system - Google Patents

Description

Description: TECHNICAL FIELD The present invention relates to a blast furnace thermal automatic control system for automatically controlling the temperature of hot metal tapped from a blast furnace.

[Prior Art] As a method for estimating the temperature of hot metal in a conventional blast furnace and managing / controlling the temperature, generally, a blast furnace operator qualitatively determines information from various sensors installed in the blast furnace and The method of evaluating the situation and making the optimum adjustment of the operating factor is adopted. However, there are individual differences in the evaluation results due to the ability and experience of operators, and therefore it is difficult to standardize the operation actions and it is difficult to estimate the hot metal temperature because the evaluation is not quantitative. there were.

Under these circumstances, a process control method for a blast furnace as disclosed in, for example, Japanese Patent Publication No. 51-30007 has been proposed. This process control method keeps the blast temperature constant and obtains the amount of direct reduction in the furnace from the measured values that can be obtained continuously during operation, and the exponential smoothed value that represents the target value of Si content in pig iron and its actual value. The blast moisture content is determined by an equation that adds a correction term to prevent long-term fluctuations in the Si content in the pig iron, and the blast moisture content determination value controls the heat balance in the furnace. ing.

Therefore, the large wave change (change of long cycle) that occurs when the blast furnace condition is controlled under calculation is corrected to realize an accurate operation.

[Problems to be Solved by the Invention] In the conventional process control method disclosed in Japanese Patent Publication No. 51-30007, the information from the sensor is analyzed and input into a model to perform a predetermined calculation. I have to. For this reason, a computer that executes the calculation uses, for example, Fortran as a language, but the calculation capacity is extremely large. Furthermore, since the blast furnace changes over time, it is necessary to change and maintain the analysis model itself, but since the analysis model itself is complicated, changing the conditions of the analysis model is a very troublesome task.

Further, as a means for solving the above problems, a maintainability can be improved by a computer system using an artificial intelligence language, for example, LISP.
When production rules are used to infer the furnace heat status using sensor information (true / false data, various sensor data) and a knowledge base, for example, IF xi = ▲ x ^j ₁ ▼ THEN A = A ₁ CF = Y ₁ IF xi = ▲ x ^j ₂ ▼ THEN A = A ₂ CF = Y _{2 It is} said that creating a program or inputting the numerical values described in the rule is complicated. There was a problem.

The present invention has been made to solve such a problem, and directly controls the furnace heat of the blast furnace to a predetermined temperature level, and as a result, a desired hot metal temperature and hot metal component are obtained. And the calculation capacity and speed of the computer when it is realized by a computer, and it is easy to add and modify rules for blast furnace thermal automation even in new situations such as aging of the blast furnace. The purpose is to obtain a control system.

[Means for Solving Problems] A blast furnace thermal automatic control system according to the present invention is based on data input means for fetching data from various sensors installed in a blast furnace at a predetermined timing, and data from the sensors, Including tuyere embedding temperature, unloading speed, pressure loss, furnace top temperature, gas utilization rate, and solution loss amount,
And means for creating various data indicating the state of the blast furnace.

Further, means for creating processing data (data showing the relationship between true and false and furnace heat) by comparing the various data with the reference data, a storage means for temporarily storing the processing data, and a blast furnace operation Knowledge base means in which various knowledge bases based on experience, achievements, and mathematical models are stored, and the furnace heat level and the furnace heat transition are inferred based on the processing data of the storage means and the knowledge base of the knowledge base means. , An inference means for determining an action amount for the blast furnace based on the inference result so that the furnace heat of the blast furnace reaches a predetermined temperature level, and a means for automatically controlling the action amount.

According to a preferred embodiment of the present invention, the inference means
A three-dimensional function having three axes of sensor information, furnace heat level or furnace heat transition, and certainty factor is used.

[Operation] In the present invention, the blast furnace data from the data input means is created into various data indicating the state of the blast furnace, and then the processing data is created based on the data. Performs inference operations as artificial intelligence based on the processed data and knowledge base,
Determine the amount of action for the blast furnace. Then, the heat of the blast furnace is automatically controlled by adjusting the operation factor based on the action. Although the blast furnace itself has a large heat capacity, and the furnace heat cannot be directly measured, in the present invention, as described above, the furnace heat level corresponding to the furnace heat temperature is based on the processing data and the knowledge base. And the furnace heat transition corresponding to the temporal change of the furnace heat are respectively inferred, and the action amount for the blast furnace is determined so that the furnace heat reaches a predetermined temperature based on these two inference results. The action amount becomes appropriate according to the furnace conditions, and the furnace heat of the blast furnace can be controlled to a predetermined temperature level with high accuracy. By controlling the furnace heat of the blast furnace with high accuracy, as a result, both the hot metal temperature and the hot metal component become desired.

[Embodiment] An embodiment of the present invention will be described below with reference to the drawings. FIG. 1 is a conceptual diagram of a blast furnace thermal automatic control system according to an embodiment of the present invention, which includes a process computer having a blast furnace operation support function, an AI dedicated processor for inference processing having AI roots, and a digital instrumentation device. The main configuration.

In the figure, (1) is a blast furnace to be controlled, (10) is a process computer having a blast furnace operation support function, and sensor data collecting means (12), file means (14), computing means (16), blast furnace control system (18) and interface buffers (19).

The sensor data collecting means (12) inputs data from various sensors, for example, a temperature sensor, a pressure sensor, a gas sensor, etc. in time series through the data scanners (11a), (11b), (11c).

The file means (14) includes a time-series file means (for normal control) and a time-series file means (for artificial intelligence), and fulfills a data banking function. The arithmetic processing means (16) includes system processing means, time series processing means (for artificial intelligence), and sensor data preprocessing means.

In this embodiment, the file means (13) in the above device is used.
The time-series file means (for artificial intelligence) is incorporated in the, the time-series processing means (for artificial intelligence) and the sensor data pre-processing means are incorporated in the computing means (16), and the interface buffer (19) is further incorporated. In this respect, there is a difference from the conventional process computer, and these devices perform preprocessing of sensor data for calculation in a small computer as an AI dedicated processor.

(20) is a small computer as a processor dedicated to AI, and includes a knowledge base (22), a common data buffer (24) and an inference engine (26) shown in FIG.
(The configurations of the above-mentioned symbols (10) and (20) are
It is basically the same as that of Japanese Patent Application No. 61-113795 filed by the same applicant. ) (30) is a CRT, and the result of the inference by the inference engine (25) is the interface buffer (19) and the file means (1).
4) is transmitted and displayed via. Reference numeral (32) is a digital instrumentation device, which is used for controlling the temperature of the blast furnace based on the result of inference by the inference engine (26). It adjusts the manipulated variable and is controlled via the interface buffer (19) and the blast furnace control system (18).

(40) is a hot stove, and (42), (44), and (46) are control valves, respectively.

The operation of this embodiment having the above configuration will be described.

(1) First, data of various sensors is sequentially read by a sensor data collecting means (12) through a data scanner (11) at a predetermined timing, and a file means (14).
Are stored in the time series file means (for normal control).

(2) The data stored in the time series file means (for normal control) of the file means (14) is processed by the sensor data preprocessing means of the arithmetic processing means (16).

In this sensor data preprocessing means, data processing regarding unloading, temperature, gas utilization rate, pig iron slag, etc. is performed. Each of these data is compared with a predetermined reference value to create a predetermined processed data, and the interface buffer (1
Store in 9).

(3) Next, the processed data stored in the interface buffer (19) is transferred to the common data buffer (24).

(4) The inference engine means (26) infers the situation in the blast furnace based on the knowledge data stored in advance in the knowledge base (22) and the processing data in the common data buffer (24).

Here, the knowledge base (22) is composed of a knowledge unit for making a furnace heat judgment, a furnace heat transition, an action judgment and an action correction as shown in FIG. 2 in consideration of inference efficiency and the like. These are the operator's knowledge and experience IF ~ TH
It is expressed by EN ~ type production rules or frames, and the CF value (Certainty Factor) is introduced as an index to show the ambiguity of each rule to enhance the reliability of inference.

Furthermore, by using a three-dimensional function, which will be described later, as a means for determining the CF value, the number of rules is reduced and maintainability is improved.

In the inference engine means (26), as shown in FIG. 2, first, the furnace heat level and the furnace heat transition are judged, and then the action amount is judged based on these judgment results. This action amount is subjected to a predetermined correction, and the result is sent to the digital instrumentation device (32) via the blast furnace control system (18).

And the control valve (42) by the digital instrumentation device (32),
The opening degrees of (44) and (46) are appropriately controlled to perform an action operation, and the furnace temperature of the blast furnace (1) is controlled to a desired value.

Next, the structure of the knowledge base and its specific inference will be described with reference to FIG.

(A) Reactor heat level judgment KS (KS (Knowlege Source); knowledge source) group; This is a knowledge base for judging the state of furnace heat at the inference start time. It consists of KS groups divided into sensor attributes and functions such as "hot metal temperature", "blast pressure", "tuyere embedding temperature", etc. Each KS group is divided into 7 levels from high to low levels. Determine the CF value distribution for the furnace heat level
The maximum confidence level is the furnace heat level at the current time.
If it is determined that the furnace heat level is extremely low, enter the tuyere condition, tap condition, etc. at any time interactively,
It has a "human judgment rule" that can capture information that cannot be obtained by sensor-related rules.

In addition, it also contains a knowledge base that can handle various conditions such as residual slag storage, hot metal composition, temperature deviation between taps and tap forms, etc.

(B) Furnace heat transition judgment KS group: The furnace heat transition is divided into 5 stages from a rapid rise to a constant to a steep fall according to the degree of change from the past to the present, and the confidence is calculated for each rank, and the maximum value thereof is obtained. The stage position of is set to the furnace heat transition state at the current time.

The knowledge base is composed of various sensors such as "hot metal temperature" and "hot metal components", etc. For "hot metal temperature" and "hot metal components", "short term transition" and "long term" It is divided into "transition" and made into a rule.

(C) Action judgment KS group; Determines the action to be taken by obtaining the furnace heat status at the current time on a matrix with the furnace heat transition and furnace heat level as axes.
FIG. 3 shows an example thereof, and in this example, the peak (maximum value) of the CF value is that the furnace heat level = 4 and the furnace heat transition = 3. The action type and the amount of action at each position on the matrix are stored as knowledge in the frame in advance. The action type is configured, for example, as shown in FIG. 4, and the action amount is quantified as shown in FIG.

When adopting an action-type action at a predetermined position, the CF value needs to reach a predetermined value. Further, in principle, all of the action amount is automatically controlled, but it is also possible to partially control the action amount (for example, G in FIG. 5).

(D) Action correction amount determination KS group: Determines the action or disturbance taken in the past and determines the correction action amount in consideration of the influence amount at the present time. The contents are composed of rules and the like which detect and respond to changes in manipulated variables such as blast humidity, blast temperature, liquid fuel, and coke ratio, and disturbances such as coke water content and falling of adhering substances.

For example, when the blast humidity is changed, the change time and the changed amount are automatically detected by the "manipulation amount change detection" rule, and the subsequent influence amount is considered as a function of time by the "blast humidity" rule. In addition, when the deposits on the furnace wall fall off, the "falling wall" rule automatically determines the drop-off point, the amount of influence on the furnace heat and the tuyere tip descent time, and determines the operation time and amount of the preliminary action to make a correction calculation. Incorporated into.

(E) Comprehensive judgment KS: Comprehensively judges the amount of action to be taken based on the judgment results of (A) to (D) above. Then, the determination result is input to the operation state determination KS together with the breeze determination KS to determine the operation state, and displayed on the CRT (30) via the screen display KS to instruct the operator about the amount of action to be taken and provide guidance. At the same time, it is fed back to the digital instrumentation device (32) to perform fully automatic control (see FIG. 1).

Next, the three-dimensional function used when obtaining the CF value in each of the above knowledge bases (A) and (B) will be described.

In a normal production rule that does not introduce this function, for example, IF (the temperature of the sensor i is in the range of T1 to T2) THEN for all related sensors.
(CF value at high heat level is C1), ..., (CF value at low heat level is Cn); IF (Temperature of sensor i is in the range of T1 to T3.) THEN
(CF value at high heat level C'1), ... (CF value at low heat level is C'n); ... It is necessary to express the rules as follows, and the inference time increases because of the huge number of rules. Moreover, there is a drawback that the adjustment of the CF value becomes extremely complicated.

FIG. 6 shows a three-dimensional function of the furnace heat transition with respect to a certain sensor information. (●) in the figure is the input value given as the boundary condition of this function.

In the figure, X to Z are: X-axis: primary treatment data (for example, solution loss carbon amount) Y-axis: furnace heat transition status (degree of change is classified into 1 to 5 stages) Z-axis: confidence (CF value) means. Here, it is shown that when the value of a certain sensor is X on the X axis, the certainty factor Zj (X) for each stage (j = 1 to 5) on the Y axis shown in FIG. 6 is obtained. After obtaining the certainty factor distribution for each information in this way, each sensor is weighted and cumulatively added to determine the overall certainty factor distribution of the furnace heat transition.

Next, a method of creating a three-dimensional function of the hot metal temperature level will be described in detail. Figure 7 shows the distribution of hot metal temperature changes during tapping. Each axis means X axis; tapping temperature Y axis; hot metal temperature Z axis; frequency of occurrence (frequency of occurrence). There is. Next, FIG. 8 shows the relationship between the hot metal temperature Ti and the tap maximum hot metal temperature Tmi at the tapping time X = Xi. Based on this figure, the three-dimensional function shown in FIG. 9 is obtained by adjusting the relationship between the tap hot metal temperature and the furnace heat and the relationship between the appearance frequency and the CF value. Since the tapping temperature is measurement information that depends on the elapsed time from the tapping start and the operating conditions, more than 30 types are prepared so that they can be used properly, and are automatically selected according to the conditions.

The above three-dimensional function is described in the frame, and the calculation procedure is given by the LISP function.

Figure 10 shows the results of the operation of fully automatic control by the injection water ratio control. For example, action D1 (water ratio-3g / Nm3) is due to the reduction in reactor heat level. Also, the action at 15:00 (water ratio-2g / Nm3) is C type (no action) at the current time, but it was taken in consideration that the coke ratio -2kg / T will drop to the tuyere later. Is.

Comparing the operation results of the present embodiment with the operation results of the conventional operator, it can be seen that the management accuracy of the hot metal temperature is improved as shown in FIG. This means that operational management has been standardized.

[Effects of the Invention] As described above, according to the present invention, processing data is created from various data installed in a blast furnace, and predetermined inference as artificial intelligence is made based on the processing data and a knowledge base based on experience and the like. As a result, the conventional experience is fully utilized and the following effects are obtained.

(1) Standardization of operation management (2) Prevention of human error (3) Stable supply of high-quality hot metal with little temperature and component changes to the next process (4) Avoiding furnace cooling (5) Labor saving (6) When the device is realized by a computer, its calculation capacity and calculation speed are improved, and rules can be easily added and modified even for new situations such as aging of the blast furnace.

[Brief description of drawings]

1 is a block diagram of a blast furnace thermal automatic control system according to an embodiment of the present invention, FIG. 2 is a block diagram showing the configuration of a knowledge base, and FIG. 3 is an explanatory diagram showing an example of an action matrix, FIG. 4 is an explanatory diagram showing an example of the type of action matrix, FIG. 5 is an explanatory diagram showing an example of the action amount, FIG. 6 is an explanatory diagram of a three-dimensional function of furnace heat transition, and FIGS. Fig. 9 is an explanatory diagram showing the method of creating a three-dimensional function of the furnace heat level, Fig. 10 is a characteristic diagram showing the results of an operation example of fully automatic control by blowing water proportional control, and Fig. 11 is an error in the hot metal temperature. It is a characteristic view showing the incidence.

Claims (2)

[Claims] 1. A data input means for taking in data from various sensors installed in a blast furnace at a predetermined timing, and a tuyere embedding temperature based on the data from the sensor,
A means for creating various data indicating the state of the blast furnace, including the unloading speed, pressure loss, furnace top temperature, gas utilization rate, and solution loss amount, and comparing the various data with the reference data to determine whether it is true or false. A means for creating data indicating the relationship with the furnace heat (hereinafter referred to as processing data), a storage means for temporarily storing the processing data, various knowledge bases based on experience, achievements, and mathematical model of blast furnace operation. Based on the stored knowledge base means, the processing data of the storage means and the knowledge base of the knowledge base means, the furnace heat level and the furnace heat transition are respectively inferred so that the furnace heat reaches a predetermined temperature level. A blast furnace thermal automatic control, comprising: an inference means for determining an action amount for the blast furnace based on an inference result; and a means for automatically controlling the action amount. Stem. 2. The inference means infers using sensor information, a furnace heat level or furnace heat transition, and a confidence factor using a three-dimensional function having three axes. Blast furnace heat automatic control system.