JP6764315B2 - Operation control system of electric furnace and operation control method of electric furnace and electric furnace - Google Patents

Description

The present invention relates to an operation control system for an electric furnace used for steelmaking, an electric furnace, and an operation control method for the electric furnace.

In the electric furnace used for steelmaking, setting items that are operating conditions for electric furnace refining are set so that the carbon concentration at the end point of the molten steel to be discharged satisfies a predetermined target value. The set values of these setting items are adjusted based on the past operation results of the electric furnace.

For example, in Patent Document 1, a regression equation is created by multiple regression analysis of past molten steel temperature measurement values and operation data, and operation data such as the measured molten steel temperature measurement data, energization amount, and oxygen supply amount are subjected to a regression equation. A method for controlling the molten steel temperature has been proposed, in which the molten steel temperature in the near future is estimated and controlled by substituting into.

Japanese Unexamined Patent Publication No. 5-181544

However, in the electric furnace, the adjustment of the setting items based on the past operation results is based on the premise that the state of the electric furnace is constant. The state of the electric furnace is not always constant. For example, since the refractory constituting the furnace wall of the electric furnace is eroded by slag, the state changes every time the electric furnace refining is repeated. Therefore, even if the setting items are adjusted based on the past operation results, there is a problem that the operation result such as the carbon concentration at the end point of the molten steel to be discharged cannot be estimated with high accuracy.

The present invention has been made in view of the above problems of the prior art, and an object of the present invention is to construct a neural network that reflects the close state of an electric furnace, for example, the carbon concentration at the end point of the molten steel to be discharged. To provide an operation control system for an electric furnace capable of estimating an operation result with high accuracy, an electric furnace equipped with the operation control system, and an operation control method for the electric furnace.

The features of the present invention for solving such a problem are as follows.
(1) An input unit that receives setting items that are operating conditions for electric furnace refining in an electric furnace operation control system, and a calculation unit that inputs the setting items into a neural network to calculate an operation result estimated value. It has a control unit that executes electric furnace refining based on the above setting items.
The calculation unit is an operation control system for an electric furnace that acquires an operation result actual measurement value of the molten steel in which the electric furnace refining is executed, and re-educates the neural network by using the setting item and the operation result actual measurement value.
(2) The calculation unit of the electric furnace according to (1) re-educates the neural network when the difference between the measured operation result value and the estimated operation result value is within a predetermined range. Operation control system.
(3) The input unit receives a plurality of setting items and an operation result target value, and the calculation unit calculates an operation result estimated value corresponding to each of the plurality of setting items, and the operation result estimated value. Specifies a setting item that satisfies the operation result target value as an operation condition, and the control unit causes the calculation unit to execute electric furnace refining based on the specified operation condition according to (1) or (2). Electric furnace operation control system.
(4) The input unit receives any of (1) to (3) as the setting item, and receives the image data generated by imaging the state in which the scrap charged into the electric furnace as an iron source is stored. The operation control system of the electric furnace according to one.
(5) The operation control system for an electric furnace according to any one of (1) to (4), wherein the operation result is the carbon concentration at the end point of the molten steel subjected to the electric furnace refining.
(6) The operation control system for an electric furnace according to any one of (1) to (4), wherein the operation result is the end point molten steel temperature of the molten steel in which the electric furnace refining is executed.

(7) An electric furnace including the operation control system for the electric furnace according to any one of (1) to (6).
(8) An input step for receiving setting items that are operating conditions for electric furnace refining, and a calculation step for inputting the setting items into a neural network to calculate an estimated operating result, which is an operation control method for the electric furnace. The electric furnace refining execution step for executing the electric furnace refining based on the setting item and the operation result actual measurement value of the molten steel for which the electric furnace refining is executed are acquired, and the setting item and the operation result actual measurement value are used. An operation control method for an electric furnace having a re-education step for re-educating the neural network.
(9) The operation control method for an electric furnace according to (8), wherein the re-education step is carried out when the difference between the actual measurement value of the operation result and the estimated value of the operation result is within a predetermined range.
(10) In the input step, a plurality of setting items and operation result target values are accepted.
In the calculation step, a plurality of operation result estimation values corresponding to the plurality of operation conditions are calculated, and among the plurality of operation result estimation values calculated in the calculation step, the operation result estimation satisfying the operation result target value. An operating condition specifying step for specifying a setting item corresponding to a value as an operating condition is further provided, and in the electric furnace refining execution step, electric furnace refining is executed based on the operating condition specified in the operating condition specifying step (8). ) Or (9). The operation control method for the electric furnace.
(11) The input step receives any of (8) to (10) as the setting item, and receives the image data generated by imaging the state in which the scrap charged into the electric furnace as an iron source is stored. The operation control method of an electric furnace according to one.
(12) The operation control method for an electric furnace according to any one of (8) to (11), wherein the operation result is the end point carbon concentration of the molten steel subjected to the electric furnace refining.
(13) The operation control method for an electric furnace according to any one of (8) to (11), wherein the operation result is the end point molten steel temperature of the molten steel in which the electric furnace refining is executed.

According to the present invention, the neural network for calculating the operation result estimated value in the electric furnace refining is re-educated by using the operation result actual measurement value such as the end point carbon concentration in the electric furnace refining carried out immediately before. The network will reflect the state of the nearest electric furnace. Then, by using such a neural network, it is possible to estimate the operation result such as the end point carbon concentration in the electric furnace with high accuracy, and thereby the refining of the electric furnace can be controlled with high accuracy.

It is sectional drawing which shows an example of the electric furnace to which the operation control system 100 of the electric furnace which concerns on this embodiment is applied. It is a functional block diagram which shows the operation control system 100 of the electric furnace which concerns on this embodiment. It is a conceptual diagram of a neural network 114. It is a flow diagram explaining the update process of the neural network by the operation control system 100 of an electric furnace. It is a flow chart explaining the specific processing of the operation condition by the operation control system 100 of an electric furnace.

Hereinafter, the present invention will be described through embodiments of the present invention, but the following embodiments do not limit the invention according to the claims. Also, not all combinations of features described in the embodiments are essential to the means of solving the invention.

FIG. 1 is a cross-sectional view showing an example of an electric furnace 10 to which the operation control system 100 of the electric furnace according to the present embodiment is applied. First, the electric furnace 10 controlled by the operation control system 100 of the electric furnace of the present embodiment will be described with reference to FIG.

The electric furnace 10 has a furnace main body 12 and a furnace lid 14 that closes the upper part of the furnace main body 12 and is detachably provided with respect to the furnace main body 12. A scrap charging device 16 is provided above the furnace body 12, and scrap or the like is charged from the scrap charging device 16 into the furnace body 12 as an iron source. The scrap charging device 16 is provided with an imaging device 18 that images the state of scrap housed in the scrap charging device 16 and generates image data.

A steel ejection port 22 for ejecting molten steel 20 is provided at the bottom portion on the outer peripheral side of the furnace body 12. Further, a work port 24 is provided on the opposite side of the steel ejection port 22 of the furnace body 12. The work port 24 can be opened and closed by the work door 26. The molten slag 28 on the molten steel 20 is discharged from the work port 24.

The arc electrode 30 penetrates the central portion of the furnace lid 14 and is vertically inserted into the furnace body 12. The arc electrode 30 is connected to an elevating device (not shown), and is moved in the vertical direction by the elevating device. When the arc electrode 30 inserted into the furnace body 12 is energized, arc plasma is generated, whereby the iron source charged in the furnace body 12 is melted.

Further, from the side surface of the furnace body 12, the burner 32 and the chute 34 are inserted into the furnace body 12. Burner gas, which is a fuel, is supplied to the burner 32, and the burner 32 cuts the iron source charged in the furnace body 12 from the side surface. Note that cutting refers to cutting the iron source from the side surface using a burner 32 to break it. The chute 34 is connected to a furnace hopper (not shown). Auxiliary raw materials, ferroalloys, carbonaceous materials, etc. are separately stored in the furnace hopper. The auxiliary raw materials, ferroalloys, carbonaceous materials, etc. stored in the furnace hopper are charged into the furnace body 12 via the chute 34.

An oxygen lance 36 for supplying oxygen gas for oxidative refining is inserted into the furnace body 12 from the work port 24. Further, a ladle 38 for receiving steel is arranged below the steel outlet 22.

Electric furnace refining of an iron source using such an electric furnace 10 is carried out by the following procedure. First, the furnace lid 14 is removed from the upper part of the furnace body 12, and the first iron source is charged into the furnace body 12 from the scrap charging device 16. After that, the furnace lid 14 and the arc electrode 30 are moved onto the furnace, and the arc electrode 30 is moved downward in the furnace body 12.

Energization is started on the arc electrode 30 while moving the arc electrode 30 downward. When the arc electrode 30 is energized, the iron source is dissolved by the arc plasma formed by the arc electrode 30. Further, by moving the arc electrode 30 downward, a boring hole is formed in the iron source. Further, the iron source is cut from the side surface of the iron source by using the burner 32 inserted from the side surface of the furnace body. The iron source charged in the furnace body 12 is melted by the arc plasma formed by the arc electrode 30 and the cutting by the burner 32.

When the iron source charged for the first time is melted and the volume of the iron source is reduced to a state where additional iron sources can be charged, the energization of the arc electrode 30 is stopped. Further, the cutting work using the burner 32 is also stopped, and the furnace lid 14 and the arc electrode 30 are moved from the upper part of the furnace to open the upper part of the furnace body 12. After that, an additional iron source is charged into the furnace body 12 from the scrap charging device 16.

After the additional iron source is charged, the furnace lid 14 and the arc electrode 30 are moved onto the furnace, and the arc electrode is energized again to melt the additionally charged iron source. The charging of the iron source into the furnace body 12 and the melting of the iron source using the arc electrode 30 and the burner 32 are carried out until a predetermined amount of iron source is charged into the furnace body 12 and melted. It is executed repeatedly.

After the dissolution of the predetermined amount of iron source is completed, while continuing to energize the arc electrode 30, a slaked material such as slaked lime, which is an auxiliary material, is added from the furnace hopper and oxygen is added from the oxygen lance 36. Is supplied and oxidative refining is carried out. Then, after the generated molten slag is discharged, a carbonaceous material or the like is added from the furnace hopper to carry out reduction refining.

The molten steel whose molten steel composition has been adjusted by oxidative refining and reduction refining is ejected from the steel ejection port 22 to the ladle 38. At the time of steel ejection, a sample for analyzing the end point carbon concentration of the molten steel is taken, and after the molten steel component including the end point carbon concentration of the molten steel is measured, the ferroalloy (SiMn, FeSi, FeMn) is adjusted to match the target component. , Metal Al, coke, etc.) is charged, and one charge of electric furnace refining is completed.

The electric furnace refining of such an electric furnace 10 is controlled by the operation control system 100 of the electric furnace. FIG. 2 is a functional block diagram showing an example of the operation control system 100 of the electric furnace according to the present embodiment. The operation control system 100 of the electric furnace includes an input unit 102, a processing unit 104, a storage unit 106, a display unit 108, and a measurement unit 109.

The operation control system 100 of the electric furnace is, for example, a general-purpose computer such as a workstation or a personal computer. The input unit 102 receives input of setting items that are operating conditions for electric furnace refining from a worker who manages the electric furnace 10. In addition, the input unit 102 receives image data showing the properties of scrap and end point carbon concentration data of molten steel from the image pickup apparatus 18. The input unit 102 is, for example, an input device such as a keyboard and a mouse, and a reading device such as an information recording medium such as a memory card.

The processing unit 104 is, for example, a CPU or the like, and controls the operation of the electric furnace 10 by using the programs and data stored in the storage unit 106 to execute a predetermined calculation. The processing unit 104 includes a calculation unit 110 that calculates an estimated end point carbon concentration using a neural network and re-educates the neural network, and a control unit 112 that controls the refining of the electric furnace 10. The end point carbon concentration is an example of the operation result. Further, as an operation result, the processing unit 104 may calculate the end point molten steel temperature.

The storage unit 106 is, for example, an information recording medium such as a flash memory capable of updating and recording, a hard disk connected by a built-in or data communication terminal, a memory card, and a reading / writing device thereof. The storage unit 106 stores in advance a program for controlling the operation of the electric furnace 10, data used during execution of the program, and the like. Further, the storage unit 106 stores a neural network 114 that inputs a setting item and outputs an estimated end point carbon concentration value. The display unit 108 is, for example, an LCD or a CRT display.

FIG. 3 is a conceptual diagram of the neural network 114 according to the present embodiment. The setting items input from the input layer of the neural network 114 include, for example, when predicting the end point carbon concentration, the melted steel weight, the molten power amount, the refining power amount, the total power amount, the total oxygen amount, and the dissolution lance. Amount of oxygen, amount of refining lance oxygen, amount of dissolution standby burner oxygen, amount of dissolution burner oxygen, amount of dissolution standby burner, amount of dissolution burner oxygen, steel output temperature, amount of H waste, amount of new loose waste, amount of A press, amount of shredder , C press amount, steel darai powder amount, dust recycling amount, pig iron powder amount, pig iron amount, self-weight scrap amount, coke amount, fresh lime amount, aluminum ash amount, coke breeze powder amount, etc. These are input from the input layer of the neural network. That is, the input layer of the neural network 114 in this embodiment is composed of a number of neurons corresponding to the above setting items.

The intermediate layer of the neural network 114 according to the present embodiment is composed of 34 layers, and the output layer is composed of one neuron whose output is the end point carbon concentration. Such a neural network is created in advance by solving an optimization problem that minimizes the error of the neural network by using the setting items in the past electric furnace refining of the electric furnace 10 and the actual data of the end point carbon concentration as teacher data. And stored in the storage unit 106.

See FIG. 2 again. Before the electric furnace refining is started, the input unit 102 receives an input of a setting item from an operator. The input unit 102 outputs the received setting item to the calculation unit 110. Further, the input unit 102 acquires the image data captured by the image pickup device 18 and outputs the image data to the calculation unit 110.

When the calculation unit 110 acquires the image data from the input unit 102, the calculation unit 110 accepts the image data as a setting item. First, in order to evaluate the contour of the scrap, the calculation unit 110 subtracts a predetermined threshold value from the RGB brightness value of each pixel in the image data, and the RGB brightness of the pixel in which any one of them is 0 or less. Set the value to 0. The threshold value may be determined using image data of various scraps in the past. The calculation unit 110 converts the image data in which the brightness value of the portion other than the scrap is 0 by using the softmax function from 0 to 1.

The calculation unit 110 reads the neural network 114 from the storage unit 106, inputs the setting items including the numerical values indicating the scrap properties acquired from the input unit 102 to the input layer of the neural network 114, and outputs the end point carbon concentration estimated value. To do. The calculation unit 110 displays the calculated end point carbon concentration estimated value on the display unit 108.

Further, the calculation unit 110 outputs the setting item to the control unit 112. The control unit 112 carries out electric furnace refining with the set item as an operating condition for electric furnace refining. After the electric furnace refining is carried out in the electric furnace 10, the measuring unit 109 measures the carbon concentration at the end point of the molten steel whose molten steel component is adjusted and is discharged to the ladle 38. The end point carbon concentration measured in this way is an actual end point carbon concentration value.

The measuring unit 109 outputs the measured value of the end point carbon concentration to the calculating unit 110. The calculation unit 110 re-educates the neural network 114 stored in the storage unit 106 by using the setting items as the operating conditions and the measured value of the carbon concentration at the end point. The calculation unit 110 adds the setting item and the measured value of the end point carbon concentration to the past electric furnace refining data, and uses the past electric furnace refining data including the set item and the measured value of the end point carbon concentration as teacher data to obtain an error of the neural network 114. Re-educate the neural network 114 by solving the minimization optimization problem.

In this way, every time the electric furnace refining is executed, the calculation unit 110 re-educates the neural network 114 by using the setting item which is the operation condition of the electric furnace refining and the measured value of the carbon concentration at the end point. As a result, the neural network 114 reflects the state of the nearest electric furnace. By using the neural network 114 that reflects the state of the nearest electric furnace, the calculation unit 110 can estimate the carbon concentration at the end point of the molten steel discharged from the electric furnace 10 with high accuracy. Then, by defining the setting items that are the operating conditions for the electric furnace refining using the estimated carbon concentration, the carbon concentration at the end point of the molten steel in the electric furnace refining can be controlled with high accuracy.

Further, in the present embodiment, a numerical value calculated using image data generated by imaging scrap is input as a setting item. The state of scrap in the scrap charging device 16 affects the solubility of scrap in the electric furnace 10. Therefore, by inputting the numerical value calculated using the image data reflecting the scrap state into the setting item, the carbon concentration at the end point of the molten steel in the electric furnace refining can be estimated with higher accuracy.

Next, the process of specifying the operating conditions by the calculation unit 110 will be described. When the calculation unit 110 performs the process of specifying the operating conditions, the input unit 102 receives a plurality of setting items and the end point carbon concentration target value from the operator. The plurality of setting items mean, for example, that there are a plurality of values for at least one of the setting items, and the end point carbon concentration target value is the target after the electric furnace refining is carried out. It means the range of carbon concentration of the molten steel.

The calculation unit 110 calculates the end point carbon estimated value corresponding to each setting item by using each setting item in which a plurality of values are combined and the neural network 114. The calculation unit 110 determines whether or not there is an estimated end point carbon value within the range of the end point carbon target value, and if there is an end point carbon estimated value within the range of the end point carbon target value, the end point carbon The setting items used to calculate the estimated values are specified as operating conditions. On the other hand, when there is no end point carbon estimated value within the range of the end point carbon target value, the calculation unit 110 displays an error display on the display unit 108 indicating that there is no end point carbon estimated value within the range of the end point carbon target value. Display. Instead of displaying the error display on the display unit 108, the calculation unit 110 may specify the setting item used for calculating the end point carbon estimated value closest to the end point carbon target value as the operating conditions. ..

The calculation unit 110 outputs the setting item specified as the operating condition to the control unit 112. The control unit 112 carries out electric furnace refining with the set item as an operating condition for electric furnace refining. The calculation unit 110 re-educates the neural network 114 stored in the storage unit 106 by using the measured value of the carbon concentration at the end point of the molten steel in which the molten steel component is adjusted and the setting items as the operating conditions.

In this way, a plurality of setting items and the end point carbon concentration target value are input from the input unit 102, and the end point carbon concentration estimated value calculated by using the neural network 114 is set so as to satisfy the end point carbon concentration target value. The item may be specified in the operating conditions of electric furnace refining. By carrying out electric furnace refining under the operating conditions specified in this way, it is possible to control the end point carbon concentration of the molten steel to be the target end point carbon concentration.

In the present embodiment, when the calculation unit 110 acquires the end point carbon concentration actual measurement value of the molten steel from the measurement unit 109, the neural network stored in the storage unit 106 using the setting item and the end point carbon concentration actual measurement value is used. An example of re-education is shown. However, the calculation unit 110 is not limited to this, and when the difference between the measured value of the end point carbon concentration of the molten steel and the estimated value of the end point carbon concentration calculated by using the neural network 114 is within a predetermined range. The neural network 114 may be retrained. The predetermined range may be determined from the range of the past actual value of the end point carbon concentration in the electric furnace refining. This makes it possible to prevent the neural network 114 from being re-educated by using the measured end point carbon concentration of the different value when the measured value of the end point carbon concentration different from the actual value is measured due to some trouble.

Further, in the present embodiment, an example in which one electric furnace 10 is controlled by the operation control system 100 of one electric furnace is shown, but the present invention is not limited to this. For example, even if the operation control system 100 of one electric furnace is connected to a plurality of electric furnaces by using a wired or wireless network, the operation control system 100 of one electric furnace controls the electric furnace refining of a plurality of electric furnaces. Good. Further, an example in which one neural network 114 is provided for one electric furnace operation control system 100 is shown, but the present invention is not limited to this. For example, one neural network 114 is shared by a plurality of electric furnace operation control systems 100. You may.

Next, the processing performed by the operation control system 100 of the electric furnace will be described. FIG. 4 is a flow chart illustrating an update process of the neural network 114 by the operation control system 100 of the electric furnace. The process shown in FIG. 4 is started when the operation control system 100 of the electric furnace is started up.

When the operator inputs the setting item from the input unit 102, the calculation unit 110 acquires the setting item (step S101). The calculation unit 110 calculates the end point carbon concentration estimated value of the molten steel by using the setting item and the neural network 114 stored in the storage unit 106 (step S102). The calculation unit 110 displays the calculated end point carbon concentration estimated value on the display unit 108 (step S103).

The control unit 112 carries out electric furnace refining with the setting items acquired from the calculation unit 110 as operating conditions (step S104). After the electric furnace refining is carried out, the calculation unit 110 acquires the measured value of the carbon concentration at the end point of the molten steel measured by the measurement unit 109 (step S105). The calculation unit 110 re-educates the neural network stored in the storage unit 106 using the setting items and the measured value of the end point carbon concentration (step S106).

The calculation unit 110 determines whether or not the termination condition of the operation control system 100 of the electric furnace is satisfied (S106). When the calculation unit 110 determines that the termination condition of the operation control system 100 of the electric furnace is satisfied (step S107: Yes), the calculation unit 110 terminates the process. On the other hand, when the calculation unit 110 determines that the termination condition of the operation control system 100 of the electric furnace is not satisfied (step S107: No), the process returns to step S101 and waits until the setting item is acquired again. To do.

By executing the process shown in FIG. 4, the operation control system 100 of the electric furnace sets the setting items which are the operating conditions of the electric furnace refining and the measured value of the carbon concentration at the end point each time the electric furnace refining is performed. The neural network 114 is retrained using it. As a result, the neural network 114 reflects the state of the nearest electric furnace. The calculation unit 110 estimates the end point carbon concentration of the molten steel discharged from the electric furnace with high accuracy by estimating the end point carbon concentration of the electric furnace using a neural network 114 that reflects the state of the nearest electric furnace. it can. Then, by determining the operating conditions for electric furnace refining using the estimated carbon concentration, the carbon concentration at the end point of the molten steel in electric furnace refining can be controlled with high accuracy.

FIG. 5 is a flow chart illustrating a process of specifying operating conditions by the operation control system 100 of the electric furnace. The process shown in FIG. 5 is also started when the operation control system 100 of the electric furnace is started up.

When the operator inputs a plurality of setting items and the end point carbon concentration target value from the input unit 102, the calculation unit 110 acquires the plurality of setting items and the end point carbon concentration target value (step S201). The calculation unit 110 calculates the end point carbon estimated value corresponding to each setting item by using each setting item and the neural network 114 (step S202). The calculation unit 110 determines whether or not there is an estimated end point carbon value within the range of the end point carbon target value (step S203). When the calculation unit 110 determines that there is an end point carbon estimated value within the range of the end point carbon target value (step S203: Yes), the calculation unit 110 specifies the setting item used for calculating the end point carbon estimated value as an operating condition. (Step S204). On the other hand, when there is no end point carbon estimated value within the range of the end point carbon target value (step S203: No), the calculation unit 110 displays an error indicating that the target value cannot be satisfied with the setting items input to the display unit 108. It is displayed (step S205), and the process returns to step S201.

The control unit 112 carries out electric furnace refining on the setting item specified by the calculation unit 110 as an operating condition (step S206). After the electric furnace refining is carried out, the calculation unit 110 acquires the measured value of the carbon concentration at the end point of the molten steel measured by the measurement unit 109 (step S207). The calculation unit 110 re-educates the neural network 114 stored in the storage unit 106 using the setting items and the measured value of the carbon concentration at the end point (step S208).

The calculation unit 110 determines whether or not the termination condition of the operation control system 100 of the electric furnace is satisfied (S209). When the calculation unit 110 determines that the termination condition of the operation control system 100 of the electric furnace is satisfied (step S209: Yes), the calculation unit 110 terminates the process. On the other hand, when the calculation unit 110 determines that the termination condition of the operation control system 100 of the electric furnace is not satisfied (step S209: No), the process returns to step S201, and the plurality of setting items and the end point are again. Wait until the carbon concentration target value is obtained.

By executing the process shown in FIG. 5, the operation control system 100 of the electric furnace can specify a setting item that satisfies the target end point carbon concentration as the operating condition of the electric furnace refining. Then, by carrying out the electric furnace refining under the operating conditions, the end point carbon concentration of the molten steel can be controlled to be the target end point carbon concentration.

In this embodiment, an example in which the end point carbon concentration is used as the operation result is shown. However, the operation is not limited to this, and the end point molten steel temperature, end point phosphorus concentration, end point sulfur concentration, end point silicon concentration or end point manganese concentration may be used as the operation result. When estimating the end point molten steel temperature using a neural network, as the setting items input from the input layer, in addition to the setting items used when estimating the end point carbon concentration, the next charge starts from the end of the previous charge. The waiting time until, the refractory temperature in the furnace body, and the water cooling panel temperature when the furnace body of the electric furnace is provided with a water cooling panel may be input.

Further, in the present embodiment, an example using the end point carbon concentration after the completion of the electric furnace refining is shown. However, the present invention is not limited to this, and as a result of the operation, the carbon concentration of the molten steel during the refining of the electric furnace may be used. When estimating the carbon concentration of molten steel during electric furnace refining using a neural network, the neural network is educated using the setting items and the actual data of the carbon concentration during electric furnace refining as educational data. Then, by using the neural network, it can be applied to the carbon concentration of the molten steel in the middle of refining the electric furnace as well as the carbon concentration at the end point.

Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various changes or improvements can be made to the above embodiments. It is clear from the description of the claims that the form with such modifications or improvements may be included in the technical scope of the present invention.

In addition, the execution order of each process of operation, procedure and step in the device, system and method shown in the claims, the specification and the drawings is specified as "before", "prior" and the like. It should be noted that the output of the previous process can be realized in any order as long as it is not used in the subsequent process. Even if the scope of claims, the specification, and the flow in the drawings are explained using "first," "next," etc. for convenience, it does not mean that it is essential to carry out in this order. Absent.

10 Electric furnace 12 Reactor body 14 Reactor lid 16 Scrap charging device 18 Imaging device 20 Molten steel 22 Outlet steel port 24 Work port 26 Work door 28 Molten slag 30 Arc electrode 32 Burner 34 Chute 36 Oxygen lance 38 Ladle 100 Ladle operation Control system 102 Input unit 104 Processing unit 106 Storage unit 108 Display unit 110 Calculation unit 112 Control unit 114 Neural network

Claims (11)

It is an operation control system for electric furnaces.
An input unit that accepts setting items that are the operating conditions for electric furnace refining,
A calculation unit that inputs the above setting items to the neural network and calculates the estimated operation result,
A control unit that executes electric furnace refining based on the above setting items,
Have,
The calculation unit acquires the operation result actual measurement value of the molten steel in which the electric furnace refining is executed, updates the neural network using the setting item and the operation result actual measurement value, and updates the neural network .
The input unit receives a plurality of setting items and an operation result target value.
The calculation unit calculates an operation result estimated value corresponding to each of the plurality of setting items, and specifies a setting item in which the operation result estimated value satisfies the operation result target value as an operation condition.
The control unit is an operation control system for an electric furnace that executes electric furnace refining based on the operating conditions specified in the calculation unit . The operation control system for an electric furnace according to claim 1, wherein the calculation unit updates the neural network when the difference between the measured operation result value and the estimated operation result value is within a predetermined range. The input unit according to any one of claims 1 and 2 receives image data generated by imaging a state in which scrap charged into an electric furnace as an iron source is stored as the setting item. The operation control system of the electric furnace described. The operation control system for an electric furnace according to any one of claims 1 to 3 , wherein the operation result is the carbon concentration at the end point of the molten steel subjected to the electric furnace refining. The operation control system for an electric furnace according to any one of claims 1 to 3 , wherein the operation result is the end point molten steel temperature of the molten steel in which the electric furnace refining is executed. An electric furnace comprising the operation control system for the electric furnace according to any one of claims 1 to 5 . It is an operation control method for electric furnaces.
Input steps that accept setting items that are the operating conditions for electric furnace refining,
A calculation step in which the above setting items are input to the neural network to calculate an operation result estimated value, and
An electric furnace refining execution step for executing electric furnace refining based on the above setting items, and
An update step of acquiring the operation result actual measurement value of the molten steel in which the electric furnace refining has been executed and updating the neural network using the setting item and the operation result actual measurement value.
Have a,
In the input step, a plurality of setting items and an operation result target value are accepted.
In the calculation step, a plurality of operation result estimates corresponding to the plurality of operation conditions are calculated.
Among the plurality of operation result estimated values calculated in the calculation step, the operation condition specifying step for specifying the setting item corresponding to the operation result estimated value satisfying the operation result target value as the operation condition is further provided.
In the electric furnace refining execution step, an operation control method of an electric furnace in which electric furnace refining is executed based on the operating conditions specified in the operating condition specifying step . The operation control method for an electric furnace according to claim 7 , wherein the update step is performed when the difference between the measured operation result value and the estimated operation result value is within a predetermined range. The electric furnace according to claim 7 or 8 , wherein the input step receives image data generated by imaging a state in which scrap charged into the electric furnace as an iron source is stored as the setting item. Operation control method. The operation control method for an electric furnace according to any one of claims 7 to 9 , wherein the operation result is the carbon concentration at the end point of the molten steel in which the electric furnace refining is executed. The operation control method for an electric furnace according to any one of claims 7 to 9 , wherein the operation result is the end point molten steel temperature of the molten steel in which the electric furnace refining is executed.

Images