JP2022036716A - Blast furnace condition determination device, blast furnace operation method, and hot metal production method - Google Patents

Abstract

To provide a blast furnace condition determination device which automatically determines and classifies the state of turbulence in the temperature distribution of a blast furnace, a blast furnace operation method which can eliminate the turbulence in the temperature distribution of the blast furnace on the basis of the results of the determination and classification by the blast furnace condition determination device, and which can enhance the automation of operation, and a hot metal production method.SOLUTION: A blast furnace condition determination device 1 for determining the furnace condition of a blast furnace, comprising: a temperature distribution measurement unit 2 for measuring a temperature distribution just above a raw material charging surface in the blast furnace; a storage unit 3 for storing a learning model learned to output a plurality of classes of patterns of temperature distribution based on the measured temperature distribution data; and a determination unit 5 for determining which of the plurality of classes the temperature distribution measured by the temperature distribution measurement unit is, using the stored learning model.SELECTED DRAWING: Figure 1

Description

The present disclosure relates to a blast furnace condition determination device, a method for operating a blast furnace, and a method for manufacturing hot metal.

In recent years, blast furnaces may be operated with a low coke ratio (CR) and a high pulverized coal injection (PCI) flow rate. In such an operating environment, it is important to grasp the furnace condition of the blast furnace early and accurately. Since the blast furnace has a cylindrical shape, if there is a bias in the circumferential direction of raw material insertion, a bias in the circumferential direction of the reaction, etc., the ironing state may vary in the circumferential direction and the operating condition may deteriorate. .. Therefore, it is especially important to detect the deviation in the circumferential direction early and accurately.

As one method of detecting the deviation in the circumferential direction, there is a method of measuring the temperature distribution directly above the raw material charging surface. It is known that this temperature distribution bias appears when at least one of the raw material charging bias and the reaction bias occurs. Conventionally, the temperature distribution directly above the raw material charging surface has often been measured by a thermocouple inserted into the furnace. The thermocouple is usually inserted from about four directions so as not to interfere with the insertion of the raw material, and the temperature at a plurality of points is measured in each radial direction. However, it was difficult to grasp the overall temperature distribution because it was limited to about four directions. Also, durable thermocouples often have slow response times. Therefore, it was difficult to capture the temperature change of the gas in response to the charging of the raw material by the raw material chute that swirls at high speed.

Here, due to recent technological improvements, it has become possible to collect the temperature distribution directly above the raw material charging surface with a high sampling cycle. This makes it possible to visualize the temperature distribution directly above the raw material charging surface in almost real time and to grasp abnormalities such as bias in the temperature distribution. However, it is difficult for humans to constantly monitor visualization information such as a screen of temperature distribution. In addition, when a human judges an abnormality, the judgment criteria are personal and it is difficult to always make an appropriate judgment. On the other hand, Patent Document 1 discloses a blast furnace condition state determination device that makes an appropriate determination by indexing the temperature variation.

Japanese Unexamined Patent Publication No. 2018-165399

Here, when an abnormality in the blast furnace condition is determined, it is preferable to control the operation of the blast furnace in order to eliminate the abnormality. However, the control content of the blast furnace for eliminating the abnormality differs depending on the state of the disorder of the temperature distribution. Therefore, there is a demand for a technique that not only detects anomalies but also determines and classifies the state of temperature distribution disorder without human intervention.

An object of the present disclosure to solve the above problems is to provide a blast furnace condition condition determination device that automatically determines and classifies the state of disturbance of the temperature distribution of the blast furnace. Another object of the present disclosure is an operation method of the blast furnace capable of eliminating the disturbance of the temperature distribution of the blast furnace based on the judgment and classification result of the blast furnace condition determination device and increasing the automation rate of the operation. The purpose is to provide a method for producing hot metal.

The blast furnace condition condition determination device according to the embodiment of the present disclosure is
It is a blast furnace condition condition determination device that determines the furnace condition condition of the blast furnace.
A temperature distribution measuring unit that measures the temperature distribution directly above the raw material charging surface in the blast furnace,
A storage unit that stores a learning model trained to output a plurality of classes for the temperature distribution pattern based on the measured temperature distribution data.
Using the stored learning model, the temperature distribution measuring unit includes a determination unit for determining which of the plurality of classes the temperature distribution measures.

The method of operating the blast furnace according to the embodiment of the present disclosure is as follows.
The operating conditions are changed according to the furnace condition of the blast furnace determined by the above-mentioned blast furnace condition determination device.

The method for producing hot metal according to the embodiment of the present disclosure is as follows.
Hot metal is manufactured using a blast furnace operated by the above-mentioned blast furnace operating method.

According to the present disclosure, it is possible to provide a blast furnace condition condition determination device that automatically determines and classifies the state of disturbance of the temperature distribution of the blast furnace. Further, according to the present disclosure, the blast furnace operation method and the hot metal that can eliminate the disturbance of the temperature distribution of the blast furnace based on the judgment and classification result of the blast furnace condition condition determination device and increase the automation rate of the operation. A manufacturing method can be provided.

FIG. 1 is a diagram showing a configuration example of a blast furnace condition state determination device according to an embodiment of the present disclosure. FIG. 2 is a diagram showing a flow of learning, determination, and display executed by the blast furnace condition determination device according to the embodiment of the present disclosure. FIG. 3 is a diagram showing a flow of learning using a convolutional neural network. FIG. 4 is a diagram illustrating a determination result. FIG. 5 is a diagram showing a configuration example of the blast furnace condition state determination device according to the modified example.

Hereinafter, an embodiment of the blast furnace condition condition determination device 1, the blast furnace operation method, and the hot metal manufacturing method for determining the furnace condition state of the blast furnace to which the present disclosure is applied will be described.

(Device configuration)
As shown in FIG. 1, the blast furnace condition state determination device 1 according to the present embodiment includes a temperature distribution measurement unit 2, a storage unit 3, a determination unit 5, and a display unit 6. Further, the blast furnace condition state determination device 1 is configured to be communicable with the learning model generation device 10, and executes input / output of the learning model and learning data to be described later with the learning model generation device 10. In the present embodiment, the learning model generation device 10 includes a learning model generation unit 4.

The temperature distribution measuring unit 2 is the temperature distribution of the space directly above the raw material charging surface, which is the uppermost surface of the layer made of the raw material charged from the top of the blast furnace, inside the blast furnace that produces pig iron from iron ore. To measure. The temperature distribution measuring unit 2 may be various sensors or devices that measure the temperature distribution directly above the raw material charging surface in the blast furnace at high speed (for example, within 10 sec). In the present embodiment, the temperature distribution measuring unit 2 is a temperature measuring device that utilizes the temperature dependence of the speed of sound. For example, the temperature distribution measurement unit 2 installs eight transceivers on the circumference of the top of the blast furnace, emits and receives sound waves toward the raw material charging surface, and measures the temperature based on the time from transmission to reception of the sound waves. Measure.

The storage unit 3 stores a learning model trained to output a plurality of classes for the temperature distribution pattern based on the measured temperature distribution data. The learning model is generated (learned) by the learning model generation unit 4, and is stored in the storage unit 3 after being learned. Further, the storage unit 3 stores the temperature distribution data measured by the temperature distribution measurement unit 2. The temperature distribution measuring unit 2 measures the temperature distribution directly above the raw material charging surface in the blast furnace in real time, and the storage unit 3 stores the temperature distribution data. When the learning model generation unit 4 generates a learning model, the temperature distribution data accumulated by the storage unit 3 is used as learning data. Further, when the determination unit 5 determines the furnace condition state of the blast furnace, the determination unit 5 acquires real-time temperature distribution data from the temperature distribution measurement unit 2 via the storage unit 3. Further, when the determination unit 5 determines the furnace condition state of the blast furnace, the learning model stored in the storage unit 3 is acquired by the determination unit 5.

The learning model generation unit 4 generates a learning model that outputs a plurality of classes of temperature distribution patterns based on the temperature distribution data stored in the storage unit 3. A class is a set or group in which the patterns of temperature distribution are classified. Details of the classes used in this embodiment will be described later.

The determination unit 5 determines the furnace condition state of the blast furnace by using the learning model (learned model) stored in the storage unit 3. In the present embodiment, in order to detect an abnormality in the state of the blast furnace, the determination unit 5 determines which of the plurality of classes the temperature distribution measured by the temperature distribution measurement unit 2 is. In this embodiment, the plurality of classes include at least two classes in which patterns of abnormal temperature distribution are classified. That is, when the determination unit 5 acquires the data of the abnormal temperature distribution, it does not simply determine that it is abnormal, but determines whether it is classified into one of a plurality of classes according to the pattern. Here, the pattern of the abnormal temperature distribution in the present embodiment includes at least the pattern of the temperature distribution that can be caused by the bias of the raw material charging and the bias of the reaction in the circumferential direction of the blast furnace.

The display unit 6 presents the determination result of the determination unit 5 to the operator by an image. The display unit 6 may further have a function of outputting sound and may issue an alarm to the operator together with the image. The operator is, for example, a worker operating a blast furnace. The furnace condition of the blast furnace determined by the blast furnace condition determination device 1 can be used to change the operating conditions in the operating method of the blast furnace. The operator who knows the abnormality of the furnace condition from the image shown on the display unit 6 changes the operating conditions of the blast furnace so as to suppress the bias of the raw material charging and the bias of the reaction in the circumferential direction of the blast furnace. Changes in the operating conditions of the blast furnace may include, for example, changes in the coke ratio. Changes in the operating conditions of the blast furnace may include, for example, changes in the air flow rate. In addition, when multiple charge control patterns such as how to charge raw materials in the circumferential direction of the blast furnace are set in advance, changing the operating conditions of the blast furnace changes the charge control pattern. May include. In addition, the above-mentioned blast furnace operation can be carried out as part of a manufacturing method for producing hot metal. In the blast furnace, the raw material iron ore is melted and reduced to pig iron, which is then released as pig iron. Impurities such as sulfur and phosphorus are removed from the hot metal discharged from the blast furnace in the hot metal pretreatment process. Further refining is performed in the converter to remove carbon.

The storage unit 3, the determination unit 5, and the display unit 6 of the blast furnace condition state determination device 1 may be realized by a computer that acquires temperature distribution data measured from the temperature distribution measurement unit 2. The computer includes, for example, a display control unit that controls a display device such as a memory (storage device), a CPU (processing device), a hard disk drive (HDD), and a display. The operating system (OS) and application programs for performing various processes can be stored in the hard disk drive, and when executed by the CPU, are read from the hard disk drive into the memory. If necessary, the CPU controls the display control unit to display a necessary image on the display. Further, the data in the process of processing is stored in the memory, and if necessary, is stored in the HDD. Various functions are realized by organically linking hardware such as a CPU and memory with an OS and necessary application programs. The storage unit 3 may be realized by, for example, a memory and a hard disk drive. The determination unit 5 may be realized by, for example, a CPU. Further, the display unit 6 may be realized by, for example, a display control unit and a display.

The learning model generation unit 4 of the learning model generation device 10 may be realized by a computer different from the blast furnace condition state determination device 1. The learning model generation unit 4 may be realized by, for example, a CPU. In the present embodiment, the trained model is stored in the storage unit 3 as described above, but as another example, it may be stored in the memory or the hard disk drive of the learning model generation device 10. In this case, the determination unit 5 may access the memory or the hard disk drive of the learning model generation device 10 to read the learned model when determining the furnace condition state of the blast furnace. Further, in the present embodiment, the learning data is stored in the storage unit 3 as described above, but as another example, it may be stored in the memory or the hard disk drive of the learning model generation device 10. In this case, the learning model generation unit 4 may access the memory or the hard disk drive of the learning model generation device 10 to read the learning data.

Here, the configuration of the blast furnace condition state determination device 1 in FIG. 1 is an example, and it is not necessary to include a part of the components. Further, the blast furnace condition condition determination device 1 may include another component. For example, the blast furnace condition state determination device 1 may have a configuration in which the display unit 6 is omitted. At this time, the blast furnace condition state determination device 1 may include a communication unit that outputs the determination result of the determination unit 5 to the terminal device of the operator via the network.

(Blast furnace condition judgment method)
FIG. 2 is a diagram showing a rough flow of the blast furnace condition condition determination method executed by the blast furnace condition condition determination device 1. The blast furnace condition determination method is divided into learning, determination, and display steps. In FIG. 2, online shows that the process is performed as part of the operation of the blast furnace. On the contrary, offline indicates that the processing is performed separately from the operation of the blast furnace.

The blast furnace condition state determination device 1 causes the learning model generation device 10 to generate a learning model offline. For example, using a command from the blast furnace condition determination device 1 as a trigger, the learning model generation unit 4 first acquires, as labeled image data, the one selected from the temperature distribution data stored in the storage unit 3. The learning model generation unit 4 generates a learning model using the labeled image data (step S1). The details of the learning model and learning will be described later. As another example, the learning model generation device 10 may start the generation of the learning model without waiting for the command from the blast furnace condition state determination device 1. That is, as long as the trained model is stored in the storage unit 3 before the determination unit 5 determines the furnace condition state, the learning model generation device 10 may take the lead in executing step S1.

The determination unit 5 reads out the learning model stored from the storage unit 3. Further, the determination unit 5 acquires real-time temperature distribution data from the temperature distribution measurement unit 2 via the storage unit 3. The determination unit 5 inputs the image data of the real-time temperature distribution into the learning model online, and determines the furnace condition state of the blast furnace (step S2). In the present embodiment, the determination unit 5 determines whether or not the real-time temperature distribution is classified into the class of the abnormal temperature distribution pattern as the determination of the furnace condition state.

After that, the display unit 6 displays the determination result of the determination unit 5 as an image (step S3). The image is not limited to a particular format as long as the operator can grasp whether or not it is classified into a class of patterns of abnormal temperature distribution. The operator who knows the abnormality of the furnace condition from the image may change the operating conditions of the blast furnace.

(Learning model)
It is known that the temperature distribution directly above the raw material charging surface becomes a concentric distribution when the raw material is normally charged, that is, when the raw material charging is not biased. It is also known that the distribution is concentric even when there is no bias in the reaction. On the contrary, when the raw materials are unevenly distributed or the raw material falling speed is uneven and the raw materials are charged unevenly, the temperature distribution is disturbed and the concentric circles are not formed. Therefore, by imaging and classifying the turbulence of the temperature distribution and letting the blast furnace furnace condition condition determination device 1 determine which turbulence the real-time temperature distribution image corresponds to, the furnace condition that does not require human intervention is required. Automatic judgment becomes possible. In the present embodiment, the learning model used for the determination is generated by learning as learning data a data having a disordered temperature distribution selected from the temperature distribution data stored in the storage unit 3.

The temperature distribution data selected as the training data includes those having an abnormal temperature distribution pattern described below when imaged. It is known that the abnormal temperature distribution pattern described below can cause anomalies in the operation of blast furnaces.

In the first pattern of abnormal temperature distribution, the high temperature portion is off the center of the raw material charging surface. Since the blast furnace is cylindrical, the shape of the raw material charging surface is circular, but the high temperature part does not include the center. Ventilation is important for blast furnaces to stabilize operations. Therefore, the raw materials are distributed so that the gas can easily pass through the center of the blast furnace. Under normal conditions, the temperature distribution directly above the raw material charging surface has a high temperature at the center. The first pattern of anomalous temperature distribution can be caused by a biased distribution of raw material charges. For example, it is possible to normalize the operation of the blast furnace by modifying the distribution of raw material charges. In the following, the class to which the temperature distribution pattern classified into the first abnormal temperature distribution pattern belongs is referred to as the first class.

In the second pattern of abnormal temperature distribution, the high temperature part is connected from the center to the periphery of the raw material charging surface. The high temperature portion includes the center of the raw material charging surface, but the high temperature portion is connected to the periphery (circumferential portion) of the raw material charging surface, and the temperature distribution is not concentric. As described above, since the temperature of the central portion is high in the normal case, the temperature of the intermediate portion (between the central portion and the periphery) is relatively low. The second pattern of anomalous temperature distribution is believed to be caused by at least one of the raw material charging bias and the reaction bias. In the following, the class to which the temperature distribution pattern classified into the second abnormal temperature distribution pattern belongs is referred to as the second class.

The temperature distribution data selected as the training data is "labeled" according to the above. For example, the image data of the temperature distribution classified into the first class may be labeled with "1", and the image data of the temperature distribution classified into the second class may be labeled with "2".

(study)
FIG. 3 is a diagram showing a flow of learning performed by the learning model generation unit 4. The learning model generation unit 4 acquires the above-mentioned learning data, creates input data and trains it, and generates a learning model. In the present embodiment, the learning model generation unit 4 learns using a convolutional neural network (hereinafter referred to as CNN), which is a method of deep learning. CNN is a method specialized in image processing capable of image recognition. Here, the learning method of the learning model generation unit 4 is not limited to the CNN, and may be another method capable of pattern image identification.

Here, the learning model generation unit 4 multi-values the temperature distribution selected as the learning data using one or more threshold values, and then uses it as the image data. In the present embodiment, the learning model generation unit 4 uses binarized image data. In the example of the image shown as the learning data in FIG. 3, the portion having a temperature higher than the threshold value corresponds to the high temperature portion and is displayed in black. The threshold is, for example, 150 ° C., but is not limited thereto. The threshold value may be set to a temperature between the temperature of the central portion and the temperature of the intermediate portion of the raw material charging surface of a normally operating blast furnace.

The learning model generation unit 4 divides the above image data into appropriate sizes (pixel sizes), takes an average for each divided data, and uses the data as input data of CNN. The learning model generation unit 4 may increase the size of the delimited image within a range in which the temperature distribution pattern can be grasped. As an example, the learning model generation unit 4 may divide the image data into 10 in each of the vertical and horizontal directions. On the contrary, when the performance of the CPU that realizes the learning model generation unit 4 is sufficiently high and the learning by the CNN can be executed within a realistic time, the learning model generation unit 4 uses the image data. It may be used as input data in pixel units without separating.

The above input data corresponds to the input layer of CNN shown in FIG. In addition, the feature amount corresponds to the intermediate layer. Further, the output layer corresponds to the determination of which of the plurality of classes the temperature distribution pattern is classified into. The learning model generation unit 4 generates a learning model by such a method. The learning model generation unit 4 may store the generated learning model in the storage unit 3. Here, the image data used as the learning data is the temperature distribution of the raw material charging surface of the blast furnace having a centrally symmetric structure. Therefore, the data obtained by rotating the image data around the center of the raw material charging surface can also be used for learning. That is, the learning model generation unit 4 can increase the number of input data and efficiently learn by using the original image data and the image data obtained by rotating the original image data.

(Judgment of abnormality)
The determination unit 5 determines the furnace condition state of the blast furnace using the learning model generated by the learning model generation unit 4. When determining the furnace condition state of the blast furnace, the determination unit 5 may read the learning model from the storage unit 3. Further, the determination unit 5 acquires real-time temperature distribution data from the temperature distribution measurement unit 2 via the storage unit 3. Similar to the learning model generation unit 4, the determination unit 5 multi-values the acquired temperature distribution using one or more threshold values and then uses it as image data. Further, the determination unit 5 divides the image data into appropriate sizes in the same manner as the learning model generation unit 4, takes an average for each of the divided data, and inputs the data to the learning model. The judgment result is obtained as the output of the learning model. In this embodiment, the output of the learning model is a plurality of classes of patterns of anomalous temperature distribution (“1” corresponding to the first class and “2” corresponding to the second class). For example, when the real-time temperature distribution is a pattern in which the high temperature portion is off-center, the learning model outputs "1". Further, for example, when the real-time temperature distribution is a pattern in which the high temperature portion is connected from the center to the periphery of the raw material charging surface, the learning model outputs "2".

The display unit 6 presents the determination result of the determination unit 5 to the operator by an image. The display unit 6 may display, for example, an image of the temperature distribution and a corresponding pattern of the abnormal temperature distribution. For example, when the learning model outputs "1", the display unit 6 may display "first class" together with the image of the temperature distribution. Here, with respect to the pattern determined not to correspond to the first class or the second class, the display unit 6 may display "third class" together with the image of the temperature distribution.

The operator may operate the blast furnace based on the determination result. For example, in the case of the first class (a pattern in which the high temperature portion is off-center), the operator performs an operation of changing the charge control pattern when different charge control patterns can be used. The operator may change the operating conditions so as to stabilize future operations, for example, in cases other than the first class. Changes in operating conditions that stabilize future operations include, for example, an increase in the coke ratio, a decrease in the PCI ratio, and a decrease in the air flow rate.

Hereinafter, the present disclosure will be specifically described with reference to Examples. The temperature distribution measuring unit 2 is a temperature measuring device that utilizes the temperature dependence of the above-mentioned sound velocity, and is provided in a blast furnace that produces pig iron. The sampling period for measuring the temperature distribution is 10 sec.

In this embodiment, the first abnormal temperature distribution pattern (the pattern in which the high temperature portion does not include the center) and the second abnormal temperature distribution pattern (the high temperature portion includes the center of the raw material charging surface). The high temperature portion was connected to the periphery of the raw material charging surface, and the temperature distribution was not concentric (a pattern) was detected.

First, the patterns of these abnormal temperature distributions were learned using CNN. As learning data, from the temperature distribution data stored in the storage unit 3, about 50 samples each corresponding to these abnormal temperature distribution patterns were selected by humans. The image data of the selected temperature distribution data was rotated by 30 ° to increase the number of samples, and then the learning was performed. The total number of the original sample and the sample obtained by rotation is about 7000. Further, in this embodiment, in order to make the abnormal pattern easy to understand, a threshold value is set for the temperature and binarization is performed. The binarization threshold was set to 150 ° C. However, the binarization operation is not an essential process of the present disclosure. That is, binarization may be omitted.

For the learning model obtained by the above learning (CNN), the determination accuracy was verified using data different from the training data. As a result of the verification, a judgment correct answer rate of 90.3% was obtained. FIG. 4 illustrates the determination result in this verification.

It was also confirmed that it is possible to distinguish (classify into the third class) the temperature distribution pattern that does not apply to either the first class or the second class.

As described above, the blast furnace condition condition determination device 1 according to the present disclosure can automatically determine and classify the state of disturbance of the temperature distribution of the blast furnace. Further, in the operation method of the blast furnace and the manufacturing method of the hot metal, it is possible to eliminate the disturbance of the temperature distribution of the blast furnace based on the result of the determination and classification of the blast furnace condition condition determination device 1 and increase the automation rate of the operation. ..

Although the present disclosure has been described with reference to the drawings and examples, it should be noted that those skilled in the art can easily make various modifications and modifications based on the present disclosure. It should be noted, therefore, that these modifications and modifications are within the scope of this disclosure. For example, the functions included in each means, each step, etc. can be rearranged so as not to be logically inconsistent, and a plurality of means, steps, etc. can be combined or divided into one. ..

In the learning of the above embodiment, image data whose high temperature portion does not include the center was selected as the pattern of the first abnormal temperature distribution. That is, the image data was selected depending on whether or not the high temperature portion included the center point of the raw material charging surface. Here, the image data may be selected depending on whether or not the central portion having a certain size and the high temperature portion overlap each other instead of the central point.

Further, as shown in FIG. 5, the blast furnace condition state determination device 1 may further include a learning model generation unit 4. That is, the blast furnace condition state determination device 1 may include a temperature distribution measurement unit 2, a storage unit 3, a learning model generation unit 4, a determination unit 5, and a display unit 6.

1 Blast furnace condition judgment device 2 Temperature distribution measurement unit 3 Storage unit 4 Learning model generation unit 5 Judgment unit 6 Display unit 10 Learning model generation unit

Claims (8)

It is a blast furnace condition condition determination device that determines the furnace condition condition of the blast furnace.
A temperature distribution measuring unit that measures the temperature distribution directly above the raw material charging surface in the blast furnace,
A storage unit that stores a learning model trained to output a plurality of classes for the temperature distribution pattern based on the measured temperature distribution data.
A blast furnace condition state determination device including a determination unit for determining which of the plurality of classes the temperature distribution measured by the temperature distribution measurement unit is based on the stored learning model. The storage unit stores the measured data of the temperature distribution, and stores the measured data.
The blast furnace condition state determination device according to claim 1, further comprising a learning model generation unit that generates a learning model that outputs a plurality of classes of the temperature distribution pattern based on the stored data. The blast furnace condition state determination device according to claim 2, wherein the learning model generation unit generates the learning model using a convolutional neural network. The blast furnace condition state determination device according to claim 2 or 3, wherein the learning model generation unit and the determination unit increase the temperature distribution to multiple values using one or more threshold values. The blast furnace condition state determination device according to any one of claims 1 to 4, wherein the learning model outputs a plurality of classes of abnormal temperature distribution patterns. The plurality of classes include a class of an abnormal temperature distribution pattern in which the high temperature portion is off the center of the raw material charging surface, and an abnormal temperature distribution in which the high temperature portion is connected from the center to the periphery of the raw material charging surface. The blast furnace condition condition determination device according to any one of claims 1 to 5, including the class of the pattern of. A method for operating a blast furnace, which changes the operating conditions according to the furnace condition of the blast furnace determined by the blast furnace condition determination device according to any one of claims 1 to 6. A method for producing hot metal using a blast furnace operated by the method for operating a blast furnace according to claim 7.

Images