KR102121910B1 - Apparatus and method for controlling blow of blast furnace - Google Patents

Abstract

The blast furnace control device includes a blast volume prediction model database that stores a blast volume prediction model for predicting the blast furnace volume, a blast volume prediction unit for obtaining a blast volume prediction value using the blast volume prediction model, a furnace temperature and a furnace for a predetermined time A furnace fluctuation index calculation unit that calculates a fluctuation index of fluctuations from fluctuations in the internal pressure, a correction unit that corrects the air flow rate prediction value based on the fluctuation fluctuation index, and a correction unit that generates a blow rate control value, and the furnace flows into the blast furnace according to the blow volume control value. It may include a blowing amount control unit for adjusting the amount of hot air supplied.

Description

Blast furnace control device and method therefor{APPARATUS AND METHOD FOR CONTROLLING BLOW OF BLAST FURNACE}

An embodiment of the present invention relates to a blast furnace blowing control device and a method therefor.

In a blast furnace, molten iron is produced by reducing iron ore of a natural product using carbon monoxide produced through the reaction of fuel with cokes and oxygen. Among the various operating factors that indicate the furnace condition (hereinafter referred to as'furnace') in the blast furnace process, breathability, indicating the degree of gas flow in the furnace, is one of the most important factors in determining the efficiency and safety of the blast furnace operation. It is one.

The operation of the blast furnace is made by melting and reducing iron ore, which receives heat by contact with the reducing gas, while the reducing gas rises in the furnace, and receives heat by contact with the reducing gas. In this process, thermal energy and reducing gas required for melting and reducing iron ore are supplied by hot air supplied through the bottom of the furnace, and for stabilization of the furnace, the amount of hot air flowing through the bottom of the furnace, that is, the amount of air blown is appropriately controlled. It is very important to do.

The amount of air blown into the furnace is adjusted according to the air permeability in the furnace. As the amount of blown air supplied into the furnace increases, the amount of molten iron produced in the blast furnace increases, but if the amount of blown air in the furnace is poor, stabilization may occur. Therefore, the operator decreases the amount of air blowing to stabilize the operation when the air permeability in the furnace is poor, and increases the amount of air blows to increase the operation efficiency when the air permeability is good in the furnace.

The air permeability inside the blast furnace varies depending on the particle size and particle size distribution of the raw materials (sintered ore, pellets, ore, etc.) and fuel (coke) charged into the furnace, and the position and shape of the softening fusing zone, which is the point where molten slag is generated, but fluctuates. It is very difficult to know the timing in advance. Typically, operators monitor the pressure gauge or thermometer attached to the furnace body in real time to determine the air permeability empirically and to determine the corresponding air flow rate.

In recent years, with the development of computerized prediction techniques, the amount of air blowing is determined by an artificial intelligence system that has learned the flow rate determining logic. However, due to the nature of the artificial intelligence system, which is difficult to analyze logic, it is difficult to determine the cause of determining the amount of air flow, and if there is an error in the input data, there is a problem such as malfunction, so the decision value is applied to the operation without verification. Difficult to do.

The problem to be solved through an embodiment of the present invention is to provide a blow control device and a method capable of verifying a blow amount prediction result according to current conditions.

The blast furnace blowing control apparatus according to an embodiment of the present invention for solving the above problems is to obtain a blowing amount prediction model database using the blowing amount prediction model database that stores a blowing amount prediction model for predicting the blowing amount of the blast furnace, and using the blowing amount prediction model Blowing air volume predicting unit, a fluctuation fluctuation index calculating unit for calculating a fluctuation fluctuation index from fluctuations in the furnace temperature and pressure within a predetermined period of time, and correcting the blowing amount prediction value based on the fluctuation fluctuation index to generate a blowing amount control It may include a correction unit, and a blowing amount control unit for adjusting the amount of hot air supplied into the blast furnace according to the blowing amount control value.

The sulfur fluctuation index calculation unit calculates temperature dispersion and pressure dispersion from the average of the temperature in the furnace and the pressure in the furnace for the predetermined time, respectively, and uses the normalized temperature dispersion and the pressure dispersion to determine the sulfur fluctuation index Can be calculated.

A plurality of temperature sensors disposed at different locations in the blast furnace to measure the temperature in the furnace, and a plurality of pressure sensors disposed at different locations in the blast furnace to measure the pressure in the furnace may be further included. .

The sulfur fluctuation index calculation unit calculates the temperature dispersion and the pressure dispersion for a plurality of locations in the blast furnace, respectively, normalizes the temperature dispersion and the pressure dispersion respectively calculated for the plurality of locations, and the plurality The sulfur fluctuation index may be calculated by using the average value of the normalized temperature variance and the normalized pressure variance for each position of.

The correcting unit judges the consistency between the fluctuation fluctuation index and the blowing amount predicted value, and outputs the blowing amount predicted value as the blowing amount control value according to the consistency determination result between the fluctuation fluctuation index and the blowing amount predicted value, or from the current blowing amount control value. The value increased or decreased may be output as the air volume control value.

The correction unit may output the predicted airflow amount as the airflow amount control value when the airflow amount increase/decrease corresponding to the fluctuation fluctuation index matches the airflow amount increase/decrease corresponding to the airflow predicted value.

The correction unit increases or decreases the current airflow control value according to whether the airflow fluctuation index corresponds to the fluctuation fluctuation index or not, if the airflow fluctuation index corresponding to the fluctuation fluctuation index is different from the airflow fluctuation index. By doing so, it can be output as the air volume control value.

The correction unit may determine that the fluctuation index of the sulfur content is greater than or equal to the first threshold value, and determine that it is a wind blow, and if the fluctuation index of fluctuation is less than the second threshold value, increase or increase the amount of blowing.

The correction unit may monitor the airflow amount predicted value for a predetermined time to calculate a standard deviation, and use the standard deviation to determine whether the airflow amount increased or decreased corresponding to the airflow amount predicted value.

The correction unit, the correction unit may correct the blowing amount control value in accordance with the facility specifications of the blast furnace, and transmit the corrected blowing amount control value to the blowing amount control unit.

The airflow control device further includes an operation data collection unit that collects operation data related to fluctuations in the blast furnace furnace, and the airflow amount prediction unit uses the operation data as input data of the airflow amount prediction model, and calculates the airflow amount prediction value. Can be obtained.

In addition, the method for controlling the blowing of a blast furnace according to an embodiment of the present invention comprises: obtaining a predicted amount of blowing air by using a blowing amount prediction model for predicting the blowing amount of the blast furnace, from fluctuations in the furnace temperature and the pressure in the furnace for a predetermined period of time. Comprising a step of calculating a fluctuation index of sulfur, by correcting the predicted amount of airflow based on the fluctuation index of fluctuations, generating a control amount of airflow, and adjusting the amount of hot air supplied to the blast furnace according to the control amount of the airflow amount can do.

The step of calculating the fluctuation index of the furnace, the temperature in the furnace and the pressure in the furnace for a plurality of positions in the blast furnace by using a plurality of temperature sensors and a plurality of pressure sensors arranged at different positions in the blast furnace Obtaining, for the plurality of positions, calculating the average of the temperature in the furnace and the pressure in the furnace for a predetermined time, respectively, calculating the temperature distribution and pressure distribution for the plurality of positions in the blast furnace, respectively Step, normalizing the temperature variance and the pressure variance for the plurality of positions, respectively, summing the average value of the temperature variance normalized for the plurality of positions and the average value of the normalized pressure variance, respectively, and changing the sulfur content. And calculating an index.

The generating of the blowing amount control value includes determining a consistency between the fluctuation fluctuation index and the blowing amount predicted value, and generating the blowing amount control value according to a result of the consistency determination between the fluctuation fluctuation index and the blowing amount predicted value. can do.

The determining of the consistency may include obtaining or not increasing or decreasing the blowing amount corresponding to the fluctuation index, obtaining or increasing or decreasing the blowing amount corresponding to the predicted blowing amount, and determining whether or not to increase or decrease the blowing amount corresponding to the fluctuation index of the yellowing, And determining whether the consistency is based on whether the amount of increase or decrease in the amount of air blowing corresponding to the predicted amount of air blows.

The step of acquiring whether or not the fluctuation amount of the blowing corresponding to the fluctuation fluctuation index is increased is determined as a wind blow if the fluctuation fluctuation index is greater than or equal to a first threshold value, and if the fluctuation fluctuation index is less than a second threshold value, it is determined to increase or maintain the blowing amount. It may include steps.

Obtaining whether the amount of increase or decrease in the amount of air blowing corresponding to the predicted amount of air blows comprises: calculating a standard deviation by monitoring the amount of air blowing predicted for a predetermined period of time, and determining whether to increase or decrease the amount of air blowing corresponding to the amount of air blowing predicted by using the standard deviation. It may include steps.

In the generating of the blowing amount control value according to the result of the determination of consistency, when the blowing amount increase/decrease corresponding to the fluctuation fluctuation index and the blowing amount increase/decrease corresponding to the blowing amount prediction value coincide with each other, the blowing amount predicted value is the blowing amount control value. It may include the step of outputting.

In the generating of the blowing amount control value according to the result of the determination of consistency, if the blowing amount increase/decrease corresponding to the fluctuation fluctuation index and the blowing amount increase/decrease corresponding to the blowing amount prediction value are different from each other, the blowing amount increase/decrease corresponding to the fluctuation fluctuation index The method may include outputting the current airflow control value as a predetermined value by increasing or decreasing the current airflow control value.

The blowing control method further includes correcting the blowing amount control value according to the facility specification of the blast furnace, and adjusting the hot air amount comprises supplying the hot air into the blast furnace according to the corrected blowing amount control value. It may include the step of adjusting the amount.

According to an embodiment of the present invention, it is possible to verify and correct the blowing amount prediction result according to the current furnace condition, so that it is possible to control the blowing amount by reacting to the furnace in real time, thereby minimizing fluctuations of the furnace furnace and consequently the blast furnace. It is possible to stabilize operation and improve efficiency.

Figure 1 shows an example of a blast furnace (blast furnace) equipment.
Figure 2 schematically shows an apparatus for controlling the blowing of a blast furnace according to an embodiment of the present invention.
3 and 4 are diagrams for explaining the correlation between the fluctuation index of the sulfur and the amount of air blowing according to an embodiment of the present invention.
5 is a diagram illustrating an example of correcting a blowing amount control value by using a sulfur fluctuation index in a blowing control apparatus according to an embodiment of the present invention.
6 schematically shows a method for controlling blowing of a blast furnace according to an embodiment of the present invention.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art to which the present invention pertains can easily practice. The present invention can be implemented in many different forms and is not limited to the embodiments described herein.

In order to clearly describe an embodiment of the present invention, parts irrelevant to the description are omitted, and the same reference numerals are assigned to the same or similar elements throughout the specification.

Throughout the specification, when a part is "connected" to another part, this includes not only "directly connected" but also "electrically connected" with another element in between. .

Hereinafter, with reference to the necessary drawings will be described in detail with respect to the blast furnace (blast furnace) blowing control device and method.

1 shows an example of a blast furnace facility.

The blast furnace facility is a facility that produces molten iron in the steel process.

Referring to FIG. 1, the blast furnace 10 is a furnace in which iron ore as a raw material is charged and melt-reduced to pig iron.

On the upper part of the blast furnace 10, a furnace hopper 11 in which raw materials or fuel charged through a charging conveyor belt 5 is stored is located. The raw material or fuel stored in the furnace hopper 11 is charged into the blast furnace 10 through a furnace charging process.

In the lower part of the blast furnace 10, a blower port 12 for introducing hot air supplied by the hot air furnace 20 into the blast furnace 10 is located. The amount of hot air supplied by the hot air furnace 20 is adjusted to the amount introduced into the blast furnace 10 (hereinafter, referred to as “air flow amount”) according to the degree of opening and closing of the blowing valve 21.

The fuel (eg, cokes) introduced into the blast furnace 10 is burned by reaction with oxygen to generate high-temperature gas (hereinafter referred to as'reduced gas'). The reducing gas contacts the iron ore charged into the blast furnace 10 while rising in the furnace. In the furnace, iron ore, which has received heat by contact with hot reducing gas, is melted and reduced by molten iron.

The molten iron that has been melt-reduced in the blast furnace 10 is stored in the lower part of the furnace, and then discharged out of the furnace through a tap hole at regular intervals.

Figure 2 schematically shows an apparatus for controlling the blowing of a blast furnace according to an embodiment of the present invention. 3 and 4 are diagrams for explaining the correlation between the fluctuation index of the sulfur and the amount of air blowing according to an embodiment of the present invention. 5 is a diagram illustrating an example of correcting a blowing amount control value by using a sulfur fluctuation index in a blowing control apparatus according to an embodiment of the present invention.

Referring to FIG. 2, the airflow control device 100 according to an embodiment of the present invention includes a sensor unit 110, an operation data collection unit 120, an operation data database 130, a learning unit 140, and an airflow prediction model It may include a database 150, a prediction unit 160, a fluctuation fluctuation index calculation unit 170, a correction unit 180, and a blowing amount control unit 190.

The sensor unit 110 may include at least one sensor for obtaining a measurement value (eg, temperature, pressure, flue gas component, etc.) used for determining sulfur in the blast furnace 10.

For example, the sensor unit 110 is a temperature sensor for measuring the temperature in the furnace, the molten iron temperature discharged from the blast furnace 10, the hot air temperature supplied into the blast furnace 10, the exhaust gas temperature in the furnace, the skin flow temperature, etc. 111). Further, for example, the sensor unit 110 may include at least one pressure sensors 112 for measuring the pressure in the furnace, the wind pressure of the hot air supplied into the blast furnace 10, and the like. In addition, for example, the sensor unit 110 may include a gas sensor 113 for detecting a component of exhaust gas (blast furnace gas) discharged from the blast furnace 10.

The operation data collection unit 120 may collect at least one operation data that can be used to determine the furnace condition of the blast furnace 10, that is, at least one operation data affecting the furnace condition of the blast furnace 10.

The operation data collection unit 120 may automatically acquire operation data through the sensor unit 110. For example, the operation data collection unit 120 may obtain temperature information such as temperature in the furnace (or furnace temperature), molten iron temperature, hot air temperature, skin flow temperature, flue gas temperature, etc. using the temperature sensor 111. . In addition, for example, the operation data collection unit 120 may obtain pressure information such as pressure in the furnace and wind pressure using the pressure sensor 112. In addition, for example, the operation data collection unit 120 may obtain the component information of the exhaust gas (blast furnace gas) discharged from the blast furnace 10 using the gas sensor 113.

The operation data collection unit 120 may receive operation data from an operator through a user input device (not shown).

The operation data collection unit 120 may receive operation data from an external facility of the blast furnace 10.

The operation data collection unit 120 may automatically acquire operation data using at least one image analysis device (not shown). For example, the operation data collection unit 120 is a raw material (sintered ore, pellets, ore, etc.) charged into the blast furnace 10 through a high-definition camera (not shown) installed on the charging conveyor belt 5 or fuel (coke. Etc.) and analyzing the image captured by the image analysis device to obtain particle size data (particle size and particle size distribution) of the charge (fuel or raw material).

The operation data collection unit 120 may store the collected operation data in a time series in the operation data database 130. In addition, the operation data collected by the operation data collection unit 120 may be displayed on the blast furnace driving screen through a display (not shown) so that the operator can check the condition of the blast furnace 10 in real time.

The learning unit 140 may learn the operation data collected by the operation data collection unit 120 as learning data for a predetermined time, and generate a model for predicting a blow rate based on a neural network algorithm. The learning unit 140 trains a neural network by using previously collected operation data and airflow control values provided by an expert (or operator) as learning data of a neural network algorithm, and is based on current operation data from the learning result. By creating a model for predicting the amount of airflow can be predicted. Here, the neural network algorithm used for learning may be composed of two or more layers of neural networks. The blowing amount prediction model generated by the learning unit 140 is stored in the blowing amount prediction model database 150 and is used to predict the blowing amount in the prediction unit 160.

The predicting unit 160 may predict the amount of air blowing corresponding to the current situation of the blast furnace 10 from the operation data, which is time series data, by using the air flow amount predicting model based on the neural network algorithm. The prediction unit 160 inputs at least some of the operation data collected in real time through the operation data collection unit 120 as time-series input data of the blowing amount prediction model, and obtains an output value of the blowing amount prediction model as a corresponding blowing amount prediction value can do.

The yellowing fluctuation index calculating unit 170 may calculate a yellowing fluctuation index that quantifies the yellowing fluctuation of the blast furnace 10 based on the pressure in the furnace and the temperature in the furnace.

The fluctuation of air permeability in the blast furnace 10, which affects the amount of air blown during blast furnace operation, is due to fluctuations of the furnace, and among various operating data, the pressure and temperature in the furnace serve as a major cause of fluctuations of the furnace. Accordingly, the furnace fluctuation index calculation unit 170 may measure the pressure in the furnace and the temperature in the furnace in real time by using the pressure sensor 112 and the temperature sensor 111 installed in the furnace to obtain the furnace fluctuation index. . On the other hand, the pressure sensor 112 used for measuring the pressure in the furnace and the temperature sensor 111 used for measuring the temperature in the furnace, so that the pressure and temperature distribution according to the position in the blast furnace 10 can be obtained, the blast furnace ( 10) It can be evenly distributed inside. For example, the pressure sensors 112 and the temperature sensors 111 are arranged in a circumferential direction divided into 0, 90, 180, and 270 degrees along the inner surface of the blast furnace 10, 9 The dogs can be divided and placed at different heights. In this case, the furnace sulfur fluctuation index calculating unit 170 uses the 36 (=4 X 9) temperature sensors 111 and 36 pressure sensors 112 disposed at different positions to monitor the temperature and pressure in the furnace in real time. Can be measured.

The furnace fluctuation index calculation unit 170 may also be used to calculate the furnace fluctuation index by bringing the pressure in the furnace and the temperature in the furnace among the operation data collected by the operation data collection unit 120.

Hereinafter, the method for calculating the fluctuation index of the yellow fluctuation of the sulfur fluctuation index calculating unit 170 will be described in detail with reference to necessary formulas.

The pressure and temperature in the furnace continue to change over time. The furnace sulfur fluctuation index calculating unit 170 uses the furnace pressure sensor 112 and the temperature sensor 113 to quantify the fluctuation of the pressure and temperature in the furnace as the furnace fluctuation index, and the furnace pressure in a predetermined time unit. And temperature.

Then, from the pressure values and temperature values measured in the last predetermined time (for example, the last 10 minutes), the pressure average value (P _i average) and the temperature average value (T _j average) according to the position in the furnace are expressed by the following equation. Calculate as 1 and 2.

[Equation 1]

[Equation 2]

In the above equations 1 and 2, i and j is a position index indicating the position in the furnace where each pressure value (P _i (N)) or temperature value (T _j (N)) is obtained, L is within the average value calculation section It shows the number of times the temperature and pressure in the furnace were measured. In addition, N is a time index indicating a point in time at which each pressure value (P _i (N)) or temperature value (T _j (N)) is obtained within the average value calculation section.

For example, the height from the bottom to the top of the blast furnace 10 is divided into 12 stages, and the pressure average value (P _i average) and temperature according to the furnace body height from the temperature and pressure in the furnace measured in 1 minute increments in the last 10 minutes. When calculating the average value (T _j average), the pressure average value (P ₁₂ average) corresponding to the 12 stages of height may be calculated as shown in Equation 3 below.

[Equation 3]

In Equation 3 above, P ₁₂ (-9) means a pressure value measured at the most recent pressure value, that is, 9 minutes before the current value.

On the other hand, when calculating the pressure average value (P _i average) according to the height of the furnace body as described above in a state in which a plurality of pressure sensors 112 installed at the same height, P _i (N) of Equation 1 above is installed at the corresponding height The pressure values measured by the plurality of pressure sensors 112 may be replaced with an average value. Similarly, the temperature average value (T _j) according to the height of the furnace body as described above in a state where there are a plurality of temperature sensors 111 installed at the same height When calculating the average), T _j (N) of Equation 2 above may be used as an average value of temperature values measured by the plurality of temperature sensors 111 installed at corresponding heights.

When the pressure average value (P _i average) and the temperature average value (T _j average) for a recent time are obtained using the above-described Equations 1 and 2, the yellowing fluctuation index calculating unit 170 uses the pressure dispersion ( P _i dispersion) and temperature dispersion (T _j dispersion) are calculated as in Equations 4 and 5 below.

[Equation 4]

[Equation 5]

When the pressure variation (P _i variance) for a recent time for each location in the furnace is calculated using the above-described Equation 4, the yellowing fluctuation index calculating unit 170 has a minimum value of the pressure variances (P _i variances) of 0, Normalize so that the maximum value is 1. In addition, similarly, when the temperature dispersion (T _j variance) for a recent time for each location in the furnace is calculated using Equation 4 described above, the minimum value of the temperature variance (T _j variance) is 0 and the maximum value is Normalize to 1.

When the pressure dispersion values and the temperature dispersion values are normalized as described above, the yellowing fluctuation index calculating unit 170 calculates an average value for the normalized pressure dispersion values and temperature dispersion values. Then, a weight is applied to the average value of the normalized pressure variance values and the average value of the normalized temperature variance values, and then summed to calculate a sulfur fluctuation index.

The compensator 180 may output a blowing amount control value based on the predicted blowing amount output from the predicting unit 160 and the fluctuation index obtained by the yellowing fluctuation index calculating unit 170.

There is a correlation between the fluctuation index of the sulfur and the amount of air blow calculated by the fluctuation index of the sulfur content. That is, referring to FIG. 3, it can be seen that the fluctuation index of the yellowing rapidly increases when the amount of blowing is decreased. Figure 4 shows the relationship between the fluctuation index and the amount of wind blowing obtained through the experiment. Referring to FIG. 4, in the fluctuation section in which the blowing amount is decreased, the yellow fluctuation index shows the average of the yellow fluctuation index as about 0.2346, and in the steam blowing section in which the blowing amount is increased, the average of the yellow fluctuation index is about 0.0672.

Accordingly, the correction unit 180 may determine the wind-sensitive section and the increase-winding section according to the fluctuation index of road conditions based on these values. For example, a section in which the fluctuation index of the sulfur content is 0.2346 or more may be determined as a sensation section, and a section in which the fluctuation index of the sulfur content is less than 0.0627 may be determined as a section for maintaining or increasing the air volume.

When the determination unit 180 determines whether the wind-sensing section or the steaming section is based on the fluctuation fluctuation index, the correcting unit 180 determines the consistency between the wind/expansion/maintenance determination result by the fluctuation fluctuation index and the blowing amount prediction value output from the prediction unit 160. .

To this end, the correction unit 180 calculates a standard deviation for a recent predetermined time (for example, the last 10 minutes) of the airflow amount prediction value output from the prediction unit 160. Then, using the calculated standard deviation, it is determined whether the predicted value of the blowing amount at the current time corresponds to maintaining, increasing, or decreasing the amount of blowing. For example, the correction unit 180 may determine that the current amount of airflow predicted corresponds to the amount of airflow maintained when the current amount of airflow predicted value is within 95% of the confidence interval. In addition, the correction unit 180 determines that the predicted amount of airflow at the current time corresponds to an increase, and the predicted amount of airflow at the current time is the 95% confidence interval when the predicted amount of airflow at the current time deviates from the 95% confidence interval. If it deviates to the lower side, it can be determined that the current airflow forecast value corresponds to the wind blow.

As described above, when the result of determining the increase or decrease in the amount of air blowing is obtained from the predicted amount of air blowing as described above, the correction unit 180 compares this with the result of determining the amount of increase or decrease in the amount of air blowing and determines the consistency between the fluctuation index and the predicted amount of air blowing. Then, the final blowing amount control value can be output according to the result of the conformity determination.

That is, the correction unit 180, if the determination result of the blowing amount increase/decrease determined from the blowing amount prediction value and the determination result of the blowing amount increase/decrease determined from the fluctuation fluctuation index, trust the blowing amount prediction value and outputs the blowing amount prediction value as the blowing amount control value. On the other hand, if the result of the determination of the increase/decrease in the airflow amount determined from the predicted amount of airflow and the result of the determination of the amount of increase/decrease in the airflow are determined from the fluctuation index, the trust is first given to the fluctuation index of the fluctuation to generate an airflow control value based on the fluctuation index of the fluctuation. For example, although it is determined that the current wind blowing section is based on the fluctuation index of the yellow road, when the predicted airflow amount indicates an increase, the correction unit 180 determines a predetermined airflow amount (for example, 25 Nm3/min) from the current airflow control value. By performing a reduction correction, a final airflow control value can be output. In addition, for example, although it is determined as the current increase section by the yellowing fluctuation index, when the predicted amount of air blow indicates the wind, the correction unit 180 may adjust the air flow of a predetermined value from the current blow amount control value (for example, 25 Nm3/min ) To perform a correction to increase the final air volume control value.

On the other hand, as described above, when the air flow rate control value is generated based on the fluctuation index and the air flow rate prediction value as described above, the air flow rate control value may be corrected once again in accordance with the specifications of the blast furnace facility. FIG. 5 shows an example of the process until the air volume control value is finally output by the correction unit 180, and the'correction air volume' is an air volume predicted value based on the fluctuation index of the wind (the'artificial intelligence predicted air volume in FIG. 5). 'Reference' represents the corrected result (air flow rate control value), and'final air volume' is the result of the calibration air volume being corrected once again in accordance with the specifications of the blast furnace facility, and the final air volume control value output from the correction unit 180. It corresponds.

On the other hand, when the final air volume control value is determined, the correction unit 180 transmits it to the air volume control unit 190. In addition, it is also possible to transmit the air volume control value to a display (not shown) so that the air volume control value is output through the blast furnace operation screen.

The blowing amount control unit 190 determines the amount of hot air supplied to the blast furnace 10, that is, the blowing amount, based on the blowing amount control value output by the correction unit 180, and controls the opening/closing degree of the blowing valve 21 in response thereto. By doing so, it is possible to control the amount of air blown into the blast furnace 10.

In the blowing control device 100 having the above-described structure, the operation data collection unit 120, the learning unit 140, the prediction unit 160, the fluctuation index change unit 170, the correction unit 180, and the blowing amount control unit The functions of 190 may be performed by a processor implemented by one or more central processing units (CPUs) or other chipsets, microprocessors, and the like.

6 schematically shows a method for controlling blowing of a blast furnace according to an embodiment of the present invention.

Referring to FIG. 6, the blower control apparatus 100 according to an embodiment of the present invention collects at least one operation data that affects the furnace condition of the blast furnace 10 (S100 ).

In the step S100, the blowing control device 100 may automatically acquire operation data through at least one sensor. In addition, the blowing control device 100 may receive operation data from an operator through a user input device (not shown). In addition, the blowing control device 100 may receive operation data from the external equipment of the blast furnace 10. In addition, the airflow control device 100 may automatically acquire operation data (eg, particle size data (particle size and particle size distribution)) of the charge using at least one image analysis device (not shown).

In the step S100, the operation data includes temperature information such as the temperature in the furnace, hot spring temperature, hot air temperature, skin flow temperature, flue gas temperature, pressure information such as furnace pressure, wind pressure, component information of flue gas (blast furnace gas), and charges. Particle size data, and the like.

When the operation data is collected through the step S100, the blowing control device 100 inputs it in real time as time-series input data of the blowing amount prediction model to obtain a blowing amount prediction value (S110). Here, the airflow prediction model can be generated through learning based on a neural network algorithm.

In addition, the blowing control device 100 calculates a sulfur fluctuation index that quantifies the fluctuation of the sulfur of the blast furnace 10 based on the pressure in the furnace and the temperature in the furnace (S120).

In the step S120, the blowing control device 100 uses the pressure sensor 112 and the temperature sensor 113 in the furnace to set the pressure and temperature fluctuations in the furnace to the fluctuation index of the furnace, and the furnace is set in a predetermined time unit. Measure my pressure and temperature. Then, the yellowing fluctuation index is calculated from the fluctuations of the pressure values and the temperature values measured in the last predetermined time (for example, the last 10 minutes).

When the fluctuation index of the sulfur is calculated through the step S120, the blowing control apparatus 100 generates a blowing amount control value by correcting the blowing amount predicted value obtained through the step S110 based on this (S130).

In the step S130, the blowing control apparatus 100 may determine the consistency between the predicted blowing amount and the fluctuation index of the road, and may generate the blowing amount control value according to the matching determination result. That is, when the airflow control device 100 coincides with the increase or decrease of the airflow amount indicated by the airflow predicted value and whether the airflow fluctuation index indicates the increase or decrease of the airflow amount, the airflow control device 100 outputs the airflow predicted value as the airflow control value. On the other hand, if the airflow control device 100 differs in whether the airflow amount indicated by the airflow rate predicted value increases or decreases or not, the airflow control device 100 firstly trusts the airborne fluctuation index to generate the airflow amount control value based on the airborne fluctuation index.

In the above step 130, when the blowing amount control value is generated based on the fluctuation index and the predicted blowing amount, the blowing control device 100 may once again correct the blowing amount control value according to the specifications of the blast furnace facility.

When the air volume control value is generated through the step S130, the airflow control device 100 controls the opening and closing degree of the airflow valve 21 based on this, thereby controlling the airflow amount flowing into the blast furnace 10 (S140).

According to the above-described embodiment, the blowing control device 100 can control the amount of blowing by reacting to the furnace in real time, thereby minimizing fluctuations in the furnace furnace and, as a result, stabilizing and improving the efficiency of the blast furnace operation.

The blow control method according to an embodiment of the present invention may be executed through software. When executed in software, the configuration means of the present invention are code segments that perform necessary tasks. The program or code segments may be stored in a computer-readable recording medium.

The computer-readable recording medium includes all types of recording devices in which data readable by a computer system is stored. Examples of computer-readable recording devices include ROM, RAM, CD-ROM, DVD_ROM, DVD_RAM, magnetic tape, floppy disk, hard disk, and optical data storage device. In addition, the computer-readable recording medium can be distributed over network-connected computer devices so that the computer-readable code is stored and executed in a distributed manner.

The drawings referenced so far and the detailed description of the described invention are merely exemplary of the present invention, which are used only for the purpose of illustrating the present invention and are used to limit the scope of the present invention as defined in the claims or the claims. It is not. Therefore, those of ordinary skill in the art can easily select and replace. In addition, those skilled in the art may omit some of the components described herein without deterioration of performance or add components to improve performance. In addition, those skilled in the art may change the order of the method steps described herein according to the process environment or equipment. Therefore, the scope of the present invention should be determined not by the described embodiments but by the claims and equivalents thereof.

5: Charge conveyor belt
10: blast furnace
20: hot stove
21: Blow valve
100: blow control device
110: sensor unit
111: temperature sensor
122: pressure sensor
113: gas sensor
120: operation data collection unit
130: operational data database
140: learning department
150: airflow prediction model database
160: prediction unit
170: yellowing fluctuation index calculation unit
180: correction unit
190: air volume control

Claims (20)

In the blast furnace blowing control device,
The air flow rate prediction model database that stores the air flow rate prediction model based on the neural network algorithm for predicting the air flow rate of the blast furnace,
A blowing amount prediction unit for obtaining a blowing amount prediction value using the blowing amount prediction model based on the neural network algorithm,
A furnace fluctuation index calculation unit that calculates a fluctuation index of sulfur from the fluctuations in the temperature and pressure in the furnace for a predetermined time,
A correction unit that generates an airflow control value by correcting the airflow predicted value based on the fluctuation index of the road; and
It includes a blowing amount control unit for adjusting the amount of hot air supplied to the blast furnace in accordance with the blowing amount control value,
The correcting unit judges the consistency between the fluctuation fluctuation index and the blowing amount predicted value, and outputs the blowing amount predicted value as the blowing amount control value according to the consistency determination result between the fluctuation fluctuation index and the blowing amount predicted value, or from the current blowing amount control value. A blowing control device that outputs a value increased or decreased by a predetermined value as the blowing amount control value. According to claim 1,
The yellowing fluctuation index calculation unit,
A blower control device for calculating temperature dispersion and pressure dispersion from the average of the temperature in the furnace and the pressure in the furnace for the predetermined time, and calculating the sulfur fluctuation index using the normalized temperature dispersion and the pressure dispersion. According to claim 2,
A plurality of temperature sensors arranged at different locations in the blast furnace to measure the temperature in the furnace, and
It is arranged at different locations in the blast furnace, the blow control device further comprises a plurality of pressure sensors for measuring the pressure in the furnace. According to claim 3,
The yellowing fluctuation index calculation unit,
The temperature dispersion and the pressure dispersion are respectively calculated for a plurality of locations in the blast furnace, the temperature dispersion and the pressure dispersion respectively calculated for the plurality of locations are respectively normalized, and respectively normalized for the plurality of locations. A blow control apparatus for calculating the sulfur fluctuation index using the average value of the temperature dispersion and the average value of the normalized pressure dispersion. delete According to claim 1,
The correction unit,
When the amount of increase or decrease in the amount of air blowing corresponding to the fluctuation index and the amount of increase or decrease of the amount of air blowing corresponding to the predicted amount of air flow coincide, the blowing control device outputs the predicted amount of air blowing as the amount of control of the blowing amount. The method of claim 6,
The correction unit,
If the amount of increase or decrease in the amount of air blowing corresponding to the fluctuation index is different from the amount of increase or decrease of the amount of air blowing corresponding to the predicted amount of fluctuation, the amount of control of the amount of air is controlled by increasing or decreasing the current amount of blow control corresponding to the fluctuation index. Blowing control device that outputs by value. The method of claim 6,
The correction unit determines a wind blow if the fluctuation index of fluctuation is greater than or equal to a first threshold value, and determines to increase or maintain the blowing amount if the fluctuation fluctuation index is less than the second threshold value. The method of claim 6,
The correction unit,
The airflow control device monitors the airflow predicted value for a predetermined time to calculate a standard deviation, and determines whether the airflow amount increased or decreased corresponding to the airflow predicted value using the standard deviation. According to claim 1,
The correction unit, the blower control device for correcting the airflow amount control value in accordance with the facility specifications of the blast furnace, and delivers the corrected airflow control value to the airflow control unit. According to claim 1,
Further comprising an operation data collection unit for collecting operation data related to the fluctuation of the furnace furnace,
The blowing amount predicting unit, using the operation data as the input data of the blowing amount prediction model, the blowing control device to obtain the blowing amount prediction value. In the blast furnace control method,
Obtaining a predicted amount of airflow using the airflow forecasting model based on a neural network algorithm that predicts the airflow of the blast furnace,
Calculating a sulfur fluctuation index from fluctuations in the temperature and pressure in the furnace for a predetermined time,
Generating a blowing amount control value by correcting the blowing amount predicted value based on the fluctuation index of the road condition, and
And adjusting the amount of hot air supplied into the blast furnace according to the control amount of the air flow,
The step of generating the air volume control value,
Determining a consistency between the fluctuation index of the road condition and the predicted value of the blowing amount, and
And generating the blowing amount control value according to a result of the determination of consistency between the fluctuation fluctuation index and the blowing amount predicted value. The method of claim 12,
The step of calculating the fluctuation index of the sulfur,
Obtaining the temperature in the furnace and the pressure in the furnace for a plurality of locations in the blast furnace by using a plurality of temperature sensors and a plurality of pressure sensors arranged at different locations in the blast furnace,
Calculating the average of the temperature in the furnace and the pressure in the furnace for a predetermined time, for the plurality of positions,
Calculating a temperature dispersion and a pressure dispersion, respectively, for a plurality of locations in the blast furnace,
Normalizing the temperature dispersion and the pressure dispersion, respectively, for the plurality of positions,
And calculating the sulfur fluctuation index by adding the average value of the normalized temperature variance and the normalized pressure variance to the plurality of positions, respectively. delete The method of claim 12,
The step of determining the consistency,
Obtaining whether to increase or decrease the amount of air blowing corresponding to the fluctuation index of the sulfur,
Obtaining whether or not the increase or decrease in the amount of airflow corresponding to the predicted amount of airflow, and
And determining whether the consistency is based on whether the amount of increase or decrease in the amount of fluctuation corresponding to the fluctuation index and the amount of increase or decrease in amount of fluctuation corresponding to the predicted amount of air flow are matched. The method of claim 15,
The step of obtaining whether or not the increase or decrease in the amount of air blowing corresponding to the fluctuation index of the sulfur is
If the fluctuation index of sulfur is greater than or equal to the first threshold, determining with a wind sensation, and
And determining whether to increase steam or maintain the blowing amount if the fluctuation index of the sulfur is less than a second threshold. The method of claim 15,
The step of obtaining whether or not the increase or decrease in the amount of air blowing corresponding to the predicted amount of air blows is performed.
Calculating a standard deviation by monitoring the predicted amount of air for a predetermined time, and
And determining whether to increase or decrease the blowing amount corresponding to the blowing amount predicted value using the standard deviation. The method of claim 15,
The step of generating the air volume control value according to the result of the consistency determination,
And if the amount of increase or decrease in the blowing amount corresponding to the fluctuation index and the amount of increase or decrease in the amount of blowing corresponding to the predicted amount of air flow coincide with each other, outputting the predicted value of the blowing amount as the control amount of the blowing amount. The method of claim 15,
The step of generating the air volume control value according to the result of the consistency determination,
If the amount of increase or decrease in the blowing amount corresponding to the fluctuation index is different from the amount of increase or decrease in the amount of blowing corresponding to the predicted amount of fluctuation, the amount of air flow control value is increased or decreased by increasing or decreasing the current blow amount control value according to the amount of fluctuation in the fluctuation index. Blowing control method comprising the step of outputting. The method of claim 12,
Comprising the step of correcting the air volume control value in accordance with the equipment specifications of the blast furnace,
Adjusting the amount of hot air,
And adjusting the amount of hot air supplied into the blast furnace according to the corrected amount of air blow control value.

Images