WO2019112207A1 - Apparatus and method for controlling amount of pulverized coal injection - Google Patents

Abstract

An apparatus for controlling an amount of pulverized coal injection into a blast furnace according to an embodiment may comprise: a prediction model database for storing a prediction model for predicting, through a neural network algorithm, an amount of pulverized coal injection; an operation data collection unit for collecting operation data related to the operation of a blast furnace; a prediction unit for acquiring a prediction value for a pulverized coal injection amount, using the operation data as input data of the prediction model; and an injection amount control unit for controlling an amount of pulverized coal injected into the blast furnace, according to the prediction value for the pulverized coal injection amount.

Description

Pulverized coal intake quantity control apparatus and method

The present invention relates to an apparatus and method for controlling a pulverized coal blowing amount.

In the blast furnace, charcoal is produced by reducing iron ore from natural sources using carbon monoxide produced through the reaction of oxygen with coke. The reducing gas generated by the reaction of coke and oxygen in the lower part of the blast furnace comes into contact with the charged iron ore while rising in the furnace, and the iron ores which are transferred by the contact with the reducing gas are melted and reduced by the molten iron.

During the blast furnace operation, the heat generated in the furnace is determined by the amount of pulverized coal injected from the coke amount and the tuyere, and is used as energy for heating and reducing the iron ore in the furnace and for maintaining the reduced iron in a molten iron state . This is one of the factors affecting the output of charter. Therefore, in order to improve the efficiency of the blast furnace operation, it is necessary to grasp the heat excess or the heat shortage state in the furnace so as to maintain the optimum energy supply in accordance with the furnace situation.

Normally, in the state of no-heat, the operator checks the temperature of the char iron discharged from the furnace through the thermocouple about three to four times a day, or confirms the silicon content in the charcoal. Based on this, the amount of pulverized coal blown is controlled.

On the other hand, there is a problem in that the existing state of the state of the hearth can not be grasped accurately due to the representative limit of the data (the molten iron temperature or the silicon content in the charcoal) and the result of the judgment depending on the operator . Therefore, in order to maintain the optimum energy supply according to the current furnace conditions, a method of controlling the amount of pulverized coal blown in accordance with the current furnace conditions is needed.

An object to be solved by the embodiments is to provide a pulverized coal injection quantity control apparatus and method which can automatically control the pulverized coal injection amount in accordance with the current situation in the furnace.

According to an aspect of the present invention, there is provided an apparatus for controlling the injection volume of blast furnace according to an embodiment of the present invention, comprising: a prediction model database storing a prediction model for predicting a pulverized coal injection amount through a neural network algorithm; A predictor for obtaining a pulverized coal intake amount predicted value by using the operation data as input data of the predictive model and a control unit for controlling the amount of pulverized coal injected into the blast furnace in accordance with the predicted pulverized coal intake amount And a blow-in amount control unit.

The operation data may include temperature information and pressure information related to the blast furnace operation, and the operation data collecting unit may automatically collect the temperature information and the pressure information using a plurality of sensors.

The neural network algorithm may be composed of a convolutional neural network.

And a learning unit that learns the operation data collected through the operation data collecting unit using the training data for a predetermined period of time to construct the prediction model.

According to another aspect of the present invention, there is provided a method for controlling a pulverized coal injection amount of a blast furnace, comprising the steps of collecting operating data related to blast furnace operation, inputting input data of a prediction model for predicting a pulverized coal injection amount through a neural network algorithm And adjusting the blowing amount of the pulverized coal injected into the blast furnace in accordance with the predicted pulverized coal injection amount value.

The operation data may include temperature information and pressure information related to the blast furnace operation, and the collecting may include automatically collecting the temperature information and the pressure information using a plurality of sensors.

The pulverized coal injection amount control method may further include a step of learning the operation data collected for a predetermined time with learning data to construct the prediction model.

According to the embodiment, it is possible to automatically control the amount of injected coal to be injected in accordance with the situation in the furnace, and to maintain the optimal energy supply in accordance with the current furnace situation.

Figure 1 shows an example of a blast furnace installation.

FIG. 2 is a view schematically showing a pulverized coal blown-in amount control apparatus according to an embodiment of the present invention.

3 is a schematic view illustrating a pulverized coal blowing rate control method 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, which will be readily apparent to those skilled in the art to which the present invention pertains. The present invention may be embodied in many different forms and is not limited to the embodiments described herein.

In order to clearly illustrate the embodiments of the present invention, portions that are not related to the description are omitted, and the same or similar components are denoted by the same reference numerals throughout the specification.

Throughout the specification, when a part is referred to as being "connected" to another part, it includes not only "directly connected" but also "electrically connected" with another part in between .

Hereinafter, an apparatus and method for controlling the injection amount of pulverized coal in a blast furnace will be described in detail with reference to necessary drawings.

Fig. 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 melted and reduced by pig iron.

The iron ore and the coke are charged into the blast furnace 10 through the charging conveyor belt 5 and then moved to the upper part of the blast furnace 10 to be charged into the blast furnace 10.

 A tuyere (11) for introducing hot air and oxygen, which are supplied through a blowing tube (13), into the blast furnace (10) is located below the blast furnace (10).

The cokes charged into the furnace in the blast furnace are combusted by the reaction with hot air and hot air flowing into the furnace through the tuyere 11 to generate a high-temperature gas (hereinafter referred to as "reducing gas") . The high-temperature reducing gas thus generated is brought into contact with the iron ore charged into the blast furnace 10 while rising in the furnace, and the iron ore, which has received heat by contact with the reducing gas at a high temperature, is melted and reduced by the molten iron.

The molten reduced molten iron in the blast furnace 10 is stored under the furnace and discharged to the outside of the furnace through a tap hole 12 at regular intervals.

On the other hand, in the blast furnace operation, pulverized coal is used as an alternative fuel for coke in order to minimize environmental pollution and to reduce the cost of manufacturing coke used as fuel. The pulverized coal is supplied from a pulverized coal storage tank (not shown), flows into the tuyere 11 through a lance 14 passing through the blowing tube 13, and blown into the furnace. The pulverized coal flowing into the furnace through the tuyere (11) is burned by hot air flowing into the furnace through the tuyere (11) to generate a high-temperature reducing gas.

FIG. 2 is a view schematically showing a pulverized coal blown-in amount control apparatus according to an embodiment of the present invention.

2, the apparatus for controlling the injection amount of pulverized coal according to the embodiment of the present invention includes an operation data collecting unit 110, a user input unit 120, a operation data database 130, a learning unit 140, A model database 150, a predicting unit 160, and a pulverized coal injection amount control unit 170. [

The operation data collecting unit 110 can collect a plurality of operation data related to blast furnace operation in real time.

Table 1 below shows examples of the operation data collected by the operation data collecting unit 110.

Table 1. Examples of operating data

In Table 1, the operating data are data on the furnace temperature, the furnace pressure, the skin flow temperature, the cross sonde measurement, the air permeability (upper, middle, lower, whole) The amount of iron ore / coke charged, the amount of slag, the flue gas temperature, the composition of the flue gas, the amount of molten iron produced, the slag composition, the molten iron temperature, the pulverized coal intake amount , Wind pressure, and the like.

The operation data collecting unit 110 can automatically acquire operation data using at least one sensor. For example, the operation data collecting unit 110 may acquire temperature information such as a furnace temperature, a molten iron temperature, a hot air temperature, a skin flow temperature, and an exhaust gas temperature using one or more temperature sensors such as a cross zone. In addition, for example, the operation data collecting unit 110 can acquire pressure information such as a furnace pressure, a wind pressure and the like using one or more pressure sensors.

The operation data collecting unit 110 may receive the operation data from the operator through the user input unit 120.

In addition, the operation data collecting unit 110 may receive operation data from an external facility.

The operation data collecting unit 110 may store the operation data collected in the operation data database 130 in a time series.

The learning unit 140 may learn the operation data collected through the operation data collection unit 110 for the predetermined period as learning data to generate a pulverized coal injection amount prediction model based on a neural network algorithm. The neural network algorithm used in the pulverized coal injection amount predicting model in the learning unit 140 is composed of a convolutional neural network (CNN). CNN is a neural network consisting of one or several convolutional layers, a pooling layer, and fully connected layers. In CNN, features are extracted from time series data through a convolutional layer and a pooling layer, and prediction is performed through classification in a fully connected layer.

In the embodiment of the present invention, the learning unit 140 may set the number of features per variable to four and set the number of time series data to eight (eight minutes) in order to generate a pulverized coal injection amount predicting model. In addition, the fully connected layer is composed of two layers, and the number of neurons in each layer is set to 100 and 50, so that learning can be performed.

When the prediction model is generated, the learning unit 140 can verify the consistency and reliability of the prediction model.

The learning unit 140 may vary the operation data and monitor the trend of the pulverized coal injection amount predicted value obtained using the predictive model to verify the consistency and reliability with respect to the predictive model.

For example, it is desirable to reduce the amount of pulverized coal blown when the molten iron temperature is high during blast furnace operation. Therefore, if the predicted model operates correctly in an environment where the molten iron temperature is high, the predicted result in the predicted model should show the result of lowering the pulverized coal intake.

The learning unit 140 automatically controls the amount of pulverized coal blown using the predictive model and verifies the consistency and reliability of the predictive model by monitoring the operation efficiency (charter output amount) and the operation stabilization state (char temperature, furnace pressure, etc.) You may.

The pulverized coal injection amount prediction model generated by the learning unit 140 is stored in the prediction model database 150 and used to predict the pulverized coal injection amount in the prediction unit 160. [

The predicting unit 160 can estimate the pulverized coal intake amount from the operation data that is time series data by using the pulverized coal injection amount predicting model based on the neural network algorithm. The predicting unit 160 inputs the operating data collected through the operating data collecting unit 110 as time series input data of the pulverized coal injection amount predicting model based on the neural network algorithm and outputs the predicted model output value as the pulverized coal injection amount predicted value Increase, decrease, maintenance, etc.).

The blowing amount control unit 170 can automatically control the amount of pulverized coal injected into the blast furnace 10 from the pulverized coal storage tank (not shown) based on the predicted pulverized coal injection amount output by the predicting unit 160. [

The functions of the operation data collecting unit 110, the learning unit 140, the predicting unit 160 and the intake amount control unit 170 in the apparatus 100 for controlling the amount of pulverized coal received by the above- processing unit, CPU) or other chipset, microprocessor, or the like.

3 is a schematic view illustrating a pulverized coal blowing rate control method of a blast furnace according to an embodiment of the present invention.

Referring to FIG. 4, the apparatus for controlling the injection amount of pulverized coal according to the embodiment of the present invention generates a pulverized coal injection amount predicting model through neural network algorithm, for example, CNN-based learning (S100).

In step S100, the pulverized coal injection quantity control device 100 collects and accumulates the operation data of the blast furnace 10 for a predetermined period of time, and uses the accumulated operation data of the time series as learning data of the neural network algorithm, You can create a model.

As the pulverized coal intake amount predicting model is generated, the pulverized coal intake control apparatus 100 continuously collects a plurality of operation data related to the blast furnace operation for predicting the pulverized coal intake amount (S110). The predicted value of the pulverized coal injection amount for the blast furnace 10 is obtained by using the continuously collected operating data of the time series as the time series input data of the pulverized coal injection amount predicting model based on the neural network algorithm (S120).

When the predicted pulverized coal injection amount is obtained, the pulverized coal intake control device 100 controls the amount of pulverized coal injected into the blast furnace 10 from the pulverized coal storage tank (not shown) based on the predicted pulverized coal intake amount (S130).

According to the above-described embodiment, the pulverized coal intake quantity control apparatus 100 estimates the pulverized coal intake amount corresponding to the real-time operating state of the blast furnace 10 by using the neural network-based prediction model generated through learning, Thereby automatically controlling the amount of pulverized coal blown. Therefore, by adjusting the amount of pulverized coal to be adjusted in accordance with the current state of the blast furnace 10, the fluctuation of the blast furnace slag can be minimized, and as a result, the blast furnace operation can be stabilized and the efficiency can be improved.

The pulverized coal blown-in amount control method according to the embodiment of the present invention can be executed through software. When executed in software, the constituent means of the present invention are code segments that perform the necessary tasks. The program or code segments may be stored on a computer readable recording medium.

A computer-readable recording medium includes all kinds of recording apparatuses in which data that can be read by a computer system is stored. Examples of the computer-readable recording device include ROM, RAM, CD-ROM, DVD-ROM, DVD-RAM, magnetic tape, floppy disk, hard disk and optical data storage device. Also, the computer-readable recording medium may be distributed over a network-connected computer device so that computer-readable code can be stored and executed in a distributed manner.

It is to be understood that both the foregoing general description and the following detailed description of the present invention are illustrative and explanatory only and are intended to be illustrative of the invention and are not to be construed as limiting the scope of the invention as defined by the appended claims. It is not. Therefore, those skilled in the art can readily select and substitute it. Those skilled in the art will also appreciate that some of the components described herein can be omitted without degrading performance or adding components to improve performance. In addition, those skilled in the art may change the order of the method steps described herein depending on the process environment or equipment. Therefore, the scope of the present invention should be determined by the appended claims and equivalents thereof, not by the embodiments described.

(Explanation of Symbols)

5: Loading conveyor belt

10: blast furnace

11: Tungus

12: Outpost

13:

14: Lance

100: Pulverized coal blowing amount control device

110: Operation data collecting unit

120: user input section

130: Operation data database

140:

150: Predictive model database

160: prediction unit

170:

Claims (8)

1. A pulverized coal blowing amount control device for a blast furnace,

   A prediction model database for storing a prediction model for predicting the pulverized coal injection amount through a neural network algorithm,

   An operation data collecting unit for collecting operation data related to the blast furnace operation,

   A predictor for obtaining a predicted pulverized coal injection amount value by using the operation data as input data of the predictive model,

   And a blowing amount control unit for controlling the blowing amount of the pulverized coal injected into the blast furnace in accordance with the predicted pulverized coal injection amount.
2. The method according to claim 1,

   Wherein the operation data includes temperature information and pressure information related to the blast furnace operation,

   Wherein the operation data collecting unit automatically collects the temperature information and the pressure information using a plurality of sensors.
3. The method according to claim 1,

   Wherein the neural network algorithm is constituted by a convolution neural network.
4. The method according to claim 1,

   Further comprising a learning unit configured to learn the operation data collected through the operation data collecting unit with learning data for a predetermined period of time to construct the prediction model.
5. A pulverized coal injection amount control method for a blast furnace installation,

   Collecting operational data related to blast furnace operation,

   Obtaining the pulverized coal injection amount predicted value by using the operation data as input data of a predictive model for predicting the pulverized coal injection amount through a neural network algorithm; and

   And adjusting a blow-in amount of the pulverized coal injected into the blast furnace in accordance with the predicted pulverized coal injection amount.
6. 6. The method of claim 5,

   Wherein the operation data includes temperature information and pressure information related to the blast furnace operation,

   Wherein the collecting step includes automatically collecting the temperature information and the pressure information using a plurality of sensors.
7. 6. The method of claim 5,

   Wherein the neural network algorithm comprises a convolution neural network.
8. 6. The method of claim 5,

   Further comprising the step of learning the operation data collected for a predetermined time with learning data to construct the prediction model.

Images