Parameter determination device, parameter determination method, program, training device, and parameter determination model

The integration of an image acquisition unit and parameter determination model automates slag removal in molten metal furnaces, enhancing efficiency by determining optimal operating parameters for the slag removal machine, thus facilitating effective slag removal.

JP2024166610APending Publication Date: 2024-11-29NIPPON STEEL CORPORATION +1
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
JP2023082815
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-19
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

Existing slag removal processes in molten metal melting furnaces rely heavily on skilled operators and lack efficient automation using artificial intelligence techniques.

Method used

An image acquisition unit acquires data from a camera to determine operating parameters for a slag removal machine, utilizing a parameter determination model to control the height and tilting angle of the slag removal member based on machine learning, enabling automated and efficient slag removal.

Benefits of technology

The solution allows for efficient removal of slag from molten metal surfaces, even with less skilled operators, by providing guidance or direct control signals for the slag removal process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024166610000001_ABST
    Figure 2024166610000001_ABST
Patent Text Reader

Abstract

To provide a technology for efficiently removing slag on a surface of molten metal.SOLUTION: An aspect of the disclosure relates to a parameter determination device comprising: an image acquisition section that acquires image data indicating a surface of molten metal in a container; and a parameter determination section that, using a parameter determination model, determines, based on the image data, an operation parameter of a slag remover indicating a height of a slag removal member for scraping out slag on the molten metal and a tilting angle of the container.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present disclosure relates to a parameter determination device, a parameter determination method, a program, a training device, and a parameter determination model. [Background technology]

[0002] Impurities (which may be called "slag" or "slag") separate from the molten metal in the melting furnace and float on the surface of the molten metal in the melting furnace. In order to remove the floating impurities (hereinafter referred to as "slag"), a slag removal operation is performed. In a typical slag removal operation, an operator operates a slag remover while visually checking the surface of the molten metal in the melting furnace or while checking an image of the molten metal surface transmitted from a camera that captures the surface of the molten metal in the melting furnace, and the slag floating in the melting furnace is scraped out of the furnace by a dragger attached to the slag remover.

[0003] To achieve efficient slag removal work, the slag remover needs to be operated by a skilled operator, and technology for automating the operation of the slag remover has been proposed. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2019-105389 A [Patent Document 2] JP 2018-179348 A [Patent Document 3] JP 2020-085395 A Summary of the Invention [Problem to be solved by the invention]

[0005] With the recent advancement of deep learning technology, artificial intelligence (AI) technology has been used in various technical fields. A technology for realizing efficient slag removal work by using a machine learning model trained on the operation of a slag remover by a skilled operator is desirable.

[0006] One objective of the present disclosure is to provide a technique for efficiently removing slag from the surface of molten metal. [Means for solving the problem]

[0007] One aspect of the present disclosure relates to a parameter determination device having an image acquisition unit that acquires image data indicating a surface of molten metal in a container, and a parameter determination unit that uses a parameter determination model to determine operating parameters of a slag remover that indicate the height of a slag removal member for scraping out slag on the molten metal and the tilting angle of the container based on the image data. Effect of the Invention

[0008] According to the present disclosure, slag on the surface of molten metal can be efficiently removed. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a schematic diagram illustrating a slag removal system according to one embodiment of the present disclosure. [Diagram 2] 2A and 2B are schematic diagrams illustrating the operation of a slag remover for scraping slag out of a smelting furnace according to one embodiment of the present disclosure. [Diagram 3] FIG. 3 is a block diagram illustrating a hardware configuration of a parameter determination device according to an embodiment of the present disclosure. [Figure 4] FIG. 4 is a block diagram illustrating a functional configuration of a parameter determination device according to an embodiment of the present disclosure. [Diagram 5] FIG. 5 is a schematic diagram illustrating a parameter determination model according to one embodiment of the present disclosure. [Figure 6]FIG. 6 is a diagram illustrating the raising and lowering operation of a dragger according to one embodiment of the present disclosure. [Figure 7] 7A and 7B are diagrams illustrating an example of surface region detection according to one embodiment of the present disclosure. [Figure 8] FIG. 8 is a block diagram illustrating a functional configuration of a training device according to an embodiment of the present disclosure. [Figure 9] FIG. 9 is a flowchart showing a parameter determination process according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.

[0011] In the following embodiments, a parameter determination apparatus is disclosed for determining operating parameters of a deslag machine for removing slag of molten metal from a melting furnace.

[0012] [Removal system] 1, a slag removal system 10 according to an embodiment of the present disclosure includes a vessel 20 for accommodating molten metal such as a melting furnace, a slag remover 30 for removing slag from the molten metal in the vessel 20, a camera 40 for capturing an image of the surface of the molten metal in the vessel 20, an operation terminal 50 for operating the slag remover 30, and a parameter determination device 100 for determining the operating parameters of the slag remover 30. In the following embodiment, the slag remover 30 includes a dragger 31, a vessel tilting unit 32, and a scraper 33, and the dragger 31 is a scraping-type slag dragger equipped with the scraper 33 at its tip.

[0013] In the slag removal system 10, the parameter determination device 100 acquires image data showing the surface of the molten metal in the container 20 captured by the camera 40, and determines operation parameters showing the height of the dragger 31 of the slag remover 30 and the tilt angle of the container 20 based on the acquired image data using the parameter determination model 60. For example, the parameter determination model 60 may be any machine learning model trained to receive image data showing the surface of the molten metal and determine the height of the dragger 31 and the tilt angle of the container 20 for effectively scraping out the floating slag from the container 20 based on the surface area of ​​the molten metal in the image data. As an example, the parameter determination model 60 is trained to reproduce the height of the dragger 31 and the tilt angle of the container 20 operated by a skilled operator who operates the slag remover 30 to efficiently remove the slag floating on the surface of the molten metal while checking the captured image of the surface of the molten metal in the container 20 tilted by the container tilting unit 32 of the slag remover 30.

[0014] For example, for a slag 21 floating on the surface of the molten metal as shown in FIG. 2A, when the parameter determination model 60 receives image data showing the surface of the molten metal in the vessel 20, it determines operational parameters indicating the height of the dragger 31 and the tilt angle of the vessel 20 as shown in FIG. 2B.

[0015] In the illustrated embodiment, the parameter determination model 60 is mounted on the parameter determination device 100, but the parameter determination model 60 according to the present disclosure is not limited to this and may be disposed in another device communicatively connected to the parameter determination device 100. In this case, the parameter determination device 100 may transmit image data to the device and receive, from the device, the operation parameters obtained from the parameter determination model 60 for the image data.

[0016] When the operation parameters are acquired, the parameter determination device 100 may present the operation parameters acquired from the parameter determination model 60 to the operation terminal 50 as guidance information for the operator of the operation terminal 50. When the guidance information is acquired, the operator can operate the operation terminal 50 according to the acquired guidance information.

[0017] Alternatively, the parameter determination device 100 may transmit the operation parameters acquired from the parameter determination model 60 to the desludging machine 30 as a control signal for controlling the operation of the desludging machine 30. When the control signal is acquired, the dragger 31 and the container tilting unit 32 can be automatically operated according to the acquired control signal.

[0018] In this manner, the parameter determination device 100 can use the parameter determination model 60 to determine, from image data showing the surface of the molten metal in the vessel 20, operation parameters indicating the height of the dragger 31 and the tilt angle of the vessel 20 based on surface area information specifying the surface of the molten metal in the vessel 20. This makes it possible to realize the operation of the deslag machine 30 suited to the surface area of ​​the molten metal in the vessel 20.

[0019] Here, the parameter determination device 100 may be realized by a computing device such as a personal computer, and may have a hardware configuration as shown in Fig. 3. That is, the parameter determination device 100 has a storage device 101, a processor 102, a user interface (UI) device 103, and a communication device 104, which are interconnected via a bus B.

[0020] The programs or instructions for realizing the various functions and processes described below in the parameter determination device 100 may be downloaded from any external device via a network or the like, or may be provided from a removable storage medium such as a CD-ROM (Compact Disk-Read Only Memory) or a flash memory.

[0021] Storage device 101 may be implemented by random access memory, flash memory, a hard disk drive, etc., and stores installed programs or instructions as well as files, data, etc. used in the execution of the programs or instructions. Storage device 101 may also include a non-transitory storage medium.

[0022] The processor 102 may be realized by one or more central processing units (CPUs), graphics processing units (GPUs), processing circuitry, etc., which may be composed of one or more processor cores, and performs various functions and processes of the parameter determination device 100 described below in accordance with programs, instructions, data such as parameters necessary to execute the programs or instructions, etc. stored in the storage device 101.

[0023] The interface device 103 realizes an interface with a user of the parameter determination device 100. For example, the user operates a keyboard, a mouse, or the like to use a GUI (Graphical User Interface) displayed on a display or a touch panel, and transmits and receives various information, data, instructions, and the like between the parameter determination device 100 and the interface device 103.

[0024] The communication device 104 is realized by various communication circuits that execute communication processes with external devices, the Internet, and communication networks such as a LAN (Local Area Network).

[0025] However, the above-described hardware configuration is merely an example, and the parameter determination device 100 according to the present disclosure may be realized by any other appropriate hardware configuration.

[0026] [Parameter determination device] Next, the parameter determining device 100 according to an embodiment of the present disclosure will be described with reference to Fig. 4. Fig. 4 is a block diagram showing a functional configuration of the parameter determining device 100 according to an embodiment of the present disclosure.

[0027] 4, the parameter determination device 100 includes an image acquisition unit 110 and a parameter determination unit 120. Each functional unit of the image acquisition unit 110 and the parameter determination unit 120 may be realized by causing the processor 102 to execute a computer program stored in the storage device 101 of the parameter determination device 100.

[0028] The image acquisition unit 110 acquires image data showing the surface of the molten metal in the vessel 20. Specifically, the image acquisition unit 110 acquires image data showing the surface of the molten metal in the vessel 20 captured by the camera 40 from the camera 40. Here, the image data may be image frames sampled from video data of the surface of the molten metal captured by the camera 40. The sampling of the image frames may be performed, for example, at the start of the slag removal operation by the dragger 31, and the sampled image frames may show the surface area of ​​the molten metal at the start of the slag removal operation. Upon acquiring the image data from the camera 40, the image acquisition unit 110 provides the acquired image data to the parameter determination unit 120. In addition, the image acquisition unit 110 may transfer the video data captured by the camera 40 to the operation terminal 50 so that the operator can check the state of the surface of the molten metal and / or the movement of the dragger 31 during the slag removal operation on the display of the operation terminal 50.

[0029] The parameter determination unit 120 uses the parameter determination model 60 to determine the operation parameters of the slag remover 30 indicating the height of the slag removal member and the tilt angle of the container 20 for scraping out the slag 21 on the molten metal based on the image data. Specifically, when the image data is acquired from the image acquisition unit 110, the parameter determination unit 120 inputs the acquired image data into the parameter determination model 60 and acquires from the parameter determination model 60 the operation parameters indicating the height of the dragger 31 and the tilt angle of the container 20 for efficiently scraping out the slag 21 floating on the surface of the molten metal in the image data.

[0030] Here, the height of the dragger 31 is not limited to the height between the platform for the container 20 and the scraper plate 33 (e.g., its tip) in the slag remover 30 as shown in Figure 2, and other indicators capable of determining the vertical distance between the tip of the scraper plate 33 and the surface of the molten metal may be used.

[0031] In one embodiment, the parameter determination unit 120 may generate guidance information for operating the slag remover 30 based on the operating parameters, and present the guidance information to the operator. Specifically, when the operating parameters are acquired from the parameter determination model 60, the parameter determination unit 120 generates guidance information for assisting the operator in operating the operating terminal 50 based on the acquired operating parameters, and may display the guidance information on the display of the operating terminal 50, and / or may notify the operator of the guidance information by voice through the speaker of the operating terminal 50. With the assistance of the guidance information, the operator can operate the operating terminal 50 to operate the dragger 31 and the container tilting unit 32 with the height of the dragger 31 and the tilting angle of the container 20 suitable for the surface area of ​​the current molten metal.

[0032] In addition, in one embodiment, the parameter determination unit 120 may output a control signal for the deslag remover 30 based on the operation parameters. Specifically, when the operation parameters are acquired from the parameter determination model 60, the parameter determination unit 120 may generate a control signal for operating the dragger 31 and the container tilting unit 32 of the deslag remover 30 based on the acquired operation parameters, and transmit the control signal to the deslag remover 30. The control signal enables the deslag remover 30 to operate the dragger 31 and the container tilting unit 32 at a height of the dragger 31 and a tilting angle of the container 20 suitable for the surface area of ​​the current molten metal.

[0033] The image acquisition unit 110 may acquire image data showing the surface of the molten metal after the slag removal operation is completed each time the slag removal member is completed. Specifically, when one slag removal operation by the dragger 31 as described above is completed, the image acquisition unit 110 may acquire image data showing the surface of the molten metal after the slag removal operation, and pass the acquired image data to the parameter determination unit 120. When the image data after the slag removal operation is acquired, the parameter determination unit 120 may use the parameter determination model 60 to determine the next operation parameters for the slag remover 30 suitable for the surface area of ​​the molten metal shown in the acquired image data. The acquisition of the image data does not necessarily have to be performed in response to the completion of one slag removal operation by the dragger 31, and the image acquisition unit 110 may acquire image data showing the surface of the molten metal after a predetermined number of slag removal operations, and pass the acquired image data to the parameter determination unit 120 in response to the completion of a predetermined number of slag removal operations. The acquisition of the image data may also be performed multiple times during one slag removal operation by the dragger 31.

[0034] [Parameter determination model] As described above, the parameter determination model 60 may be realized by any machine learning model that receives image data showing the surface of the molten metal in the vessel 20 and outputs operation parameters indicating the height of the dragger 31 and the tilt angle of the vessel 20. Specifically, the parameter determination model 60 may be trained by training data consisting of image data showing the surface of the molten metal in the vessel 20 and ground-truth operation parameters indicating the height of the dragger 31 and the tilt angle of the vessel 20. For example, the parameter determination model 60 may be realized by a statistical model such as a multiple regression model, a neural network such as a convolutional neural network, or any other type of machine learning model.

[0035] For example, as shown in Fig. 5, the parameter determination model 60 may be trained by the training device 70 using training data stored in the training data database (DB) 80, and the trained model may be used as the parameter determination model 60. When the parameter determination model 60 receives image data showing the surface of the molten metal in the vessel 20 as input and generates operation parameters for the skimmer 30 indicating the height of the dragger 31 and the tilt angle of the vessel 20 as output, each training data may be composed of a pair of image data showing the surface of the molten metal and correct operation parameters indicating the height of the dragger 31 and the tilt angle of the vessel 20. For example, when the parameter determination model 60 is realized by a neural network, the training device 70 may input the training image data to the input layer of the neural network to be trained, and update the parameters of the neural network to be trained according to a comparison result between the operation parameters acquired from the output layer and the corresponding correct operation parameters.

[0036] Such a correct operation parameter may be generated based on the operation data of the scraper 30 by a skilled operator. For example, the time series data shown in FIG. 6 shows an example of the raising and lowering operation of the dragger 31 by a skilled operator when scraping out the slag 21 on the molten metal in the container 20 tilted at a certain tilt angle. In the time series data shown in FIG. 6, the dragger 31 is lowered at time t3, and the operation terminal 50 is instructed to stop the lowering operation at time t4. Then, the operator raises the dragger 31 at time t5, and instructs the operation terminal 50 to stop the raising operation at time t6. The height of the dragger 31 or the scraper 33 lowered by this lowering operation may be used as the correct height of the dragger 31, and the tilt angle of the container 20 at that time may be used as the correct tilt angle of the container 20. The dragger 31 is controlled so as to only descend to the height of the dragger 31 set by the operation parameters. That is, even if the operator operates the dragger 31 to descend, the dragger 31 is set so that it can only descend to a height indicated by the operation parameters.

[0037] In one embodiment, the parameter determination unit 120 may generate surface area information that identifies a surface area of ​​the molten metal in the container 20. Here, the surface area information may indicate the position and shape of the surface area of ​​the molten metal in the container 20. For example, if the container 20 is pot-shaped, the surface of the molten metal in the tilted container 20 may be elliptical. In this case, the surface area information may indicate the center position and shape of the elliptical surface area in three-dimensional space. For example, when the parameter determination unit 120 acquires image data from the image acquisition unit 110, the parameter determination unit 120 may perform any known ellipse fitting process on the acquired image data to extract the surface area of ​​the molten metal in the image data.

[0038] Specifically, when image data as shown in FIG. 7A is acquired, the parameter determination unit 120 may execute any known ellipse fitting process to extract an ellipse as shown by the dashed line in FIG. 7B. Typically, the boundary between the sidewall of the container 20 and the surface of the molten metal can be visually detected by a brightness difference or the like, and the elliptical surface area of ​​the molten metal can be extracted by image processing. When the shape of the ellipse is detected in this manner, the parameter determination unit 120 may derive the center coordinates of the ellipse in a three-dimensional space based on the shape of the ellipse, the tilt angle of the container 20 at the time of shooting, and the relative position and orientation of the camera with respect to the pot stand. The parameter determination unit 120 may input the center position and shape of the ellipse that defines the derived surface area to the parameter determination model 60, and obtain operation parameters indicating the height of the dragger 31 and the tilt angle of the container 20 from the parameter determination model 60.

[0039] In this case, the parameter determination model 60 may be realized as a multiple regression model that receives the center position and shape of the ellipse (e.g., the length of the major axis and the length of the minor axis) as explanatory variables and outputs operation parameters indicating the height of the dragger 31 and the tilt angle of the container 20 as objective variables. For example, the parameter determination model 60 may be a multiple regression model derived from operation data indicating the height of the dragger 31 and the tilt angle of the container 20 set by a skilled operator who has confirmed the surface area corresponding to the center position and shape of the ellipse.

[0040] In one embodiment, brightness distribution data showing the brightness distribution in the image data may be input to the parameter determination model 60. The temperature of the molten metal is significantly higher than the temperature of the slag 21, and a significant brightness difference may occur between the surface area of ​​the molten metal and the side wall of the container 20 in the image data acquired by imaging the surface of the molten metal. For this reason, the parameter determination model 60 may be trained by training data consisting of brightness distribution data showing the brightness distribution in the image data and correct operation parameters showing the height of the dragger 31 and the tilt angle of the container 20. In this case, the parameter determination unit 120 may derive brightness distribution data from the image data as a preprocessing and input the derived brightness distribution data to the parameter determination model 60 in order to use the parameter determination model 60 trained in this way. In this way, by using the brightness distribution data, the parameter determination model 60 may be able to better identify the surface area in the container 20 and better determine the operation parameters.

[0041] [Training device] Next, a training device 70 according to an embodiment of the present disclosure will be described with reference to Fig. 8. The training device 70 can be realized as a computing device such as a server, and can be realized by a hardware configuration similar to that of the parameter determination device 100 shown in Fig. 3, without being limited thereto. Fig. 8 is a block diagram showing a functional configuration of the training device 70 according to an embodiment of the present disclosure. As shown in Fig. 8, the training device 70 has a data acquisition unit 71 and a training unit 72.

[0042] The data acquisition unit 71 acquires training data for training the parameter determination model 60. The training data may be composed of, for example, image data showing the surface of the molten metal in the vessel 20 and correct operation parameters showing the height of the slag removal member and the tilt angle of the vessel 20 for scraping out the slag 21 on the molten metal. The training data may be preferably generated based on operation data of the slag remover 30 by a skilled operator, and may be composed of the height of the dragger 31 and the tilt angle of the vessel 20 for effectively scraping out the floating slag from the vessel 20 based on the surface area of ​​the molten metal in the image data.

[0043] The training unit 72 uses the training data to train the parameter determination model 60. For example, when the parameter determination model 60 is realized by a neural network, the training unit 72 inputs image data of the training data to the parameter determination model 60 to be trained, and acquires an output result from the parameter determination model 60 to be trained. Then, the training unit 72 compares the acquired output result with the correct action parameters of the training data, and adjusts the parameters of the parameter determination model 60 according to the backpropagation method based on the error between the output result and the correct action parameters. The finally acquired parameter determination model 60 is provided to the parameter determination device 100.

[0044] The parameter determination model 60 obtained in this manner can, when it acquires image data showing the surface of the molten metal in the container 20, determine the operating parameters of the slag remover 30 indicating the height of the slag removal member for scraping out the slag 21 on the molten metal and the tilting angle of the container 20 based on the image data.

[0045] [Parameter determination process] Next, a parameter determination process according to an embodiment of the present disclosure will be described with reference to Fig. 9. The parameter determination process is executed by the above-mentioned parameter determination device 100, and more specifically, may be realized by one or more processors 102 of the parameter determination device 100 executing one or more programs or instructions stored in one or more storage devices 101. Fig. 9 is a flowchart showing the parameter determination process according to an embodiment of the present disclosure.

[0046] 9, in step S101, the parameter determining device 100 acquires image data of the surface of the molten metal in the container 20. Specifically, the parameter determining device 100 acquires image data showing the surface region of the molten metal in the container 20 from the camera 40 disposed above the container 20.

[0047] In step S102, the parameter determination device 100 generates operation parameters indicating the height of the slag removal member and the tilt angle of the vessel 20 using the parameter determination model 60. Specifically, the parameter determination device 100 inputs the acquired image data and / or brightness distribution data derived from the image data to the parameter determination model 60, and obtains operation parameters indicating the height of the dragger 31 and the tilt angle of the vessel 20 from the parameter determination model 60. The parameter determination model 60 may be trained to generate operation parameters based on a surface area of ​​the molten metal in the vessel 20.

[0048] For example, the parameter determination model 60 may be a neural network trained to receive image data and / or brightness distribution data as input and output operation parameters indicating the height of the dragger 31 and the tilt angle of the container 20. The parameter determination device 100 may also execute an ellipse fitting process for the image data and / or brightness distribution data to extract an elliptical surface area of ​​the molten metal in the container 20 and derive the center position and shape of the extracted ellipse. Thereafter, the parameter determination device 100 may input the center position and shape of the ellipse derived as explanatory variables of the parameter determination model 60 realized as a multiple regression model, and obtain operation parameters indicating the height of the dragger 31 and the tilt angle of the container 20 as objective variables.

[0049] In step S103, the parameter determination device 100 may present the operation parameters as guidance information for operating the scraper 30. Specifically, the parameter determination device 100 may generate guidance information for guiding the operator based on the acquired operation parameters, and transmit the guidance information to the operation terminal 50. Upon acquiring the guidance information, the operation terminal 50 may display the guidance information on a display to guide the operation of the scraper 30 by the operator, and / or may notify the guidance information via a speaker. The operation terminal 50 raises and lowers the dragger 31 by the operator's raising and lowering operation of the dragger 31, but does not lower the dragger 31 beyond the height of the dragger 31 indicated in the operation parameters.

[0050] Alternatively, the parameter determination device 100 may output a control signal for operating the dragger 31 and the container tilting unit 32 to the dessing machine 30. Specifically, the parameter determination device 100 may generate a control signal for operating the dragger 31 and the container tilting unit 32 and transmit the control signal to the dessing machine 30. Upon receiving the control signal, the dessing machine 30 operates the dragger 31 and the container tilting unit 32 in accordance with the control signal.

[0051] In step S104, the parameter determining device 100 determines whether to end the slag removing operation. For example, the parameter determining device 100 may determine whether the slag removing operation has been completed a predetermined number of times, and may end the parameter determining process when the slag removing operation has been completed a predetermined number of times. Alternatively, the parameter determining device 100 may end the parameter determining process when a predetermined time has elapsed since the start of the slag removing operation. Alternatively, the parameter determining device 100 may end the parameter determining process when the amount of slag remaining in the container 20 and / or the amount of slag most recently removed becomes equal to or less than a predetermined threshold. On the other hand, if the slag removing operation has not been completed a predetermined number of times, if the predetermined time has not elapsed since the start of the slag removing operation, or if the amount of slag remaining in the container 20 and / or the amount of slag most recently removed does not become equal to or less than a predetermined threshold, the parameter determining device 100 returns to step S101 and continues the slag removing operation.

[0052] According to the above-described embodiment, it is possible to obtain the operation parameters for the deslag machine 30 suitable for the surface area of ​​the molten metal by utilizing the parameter determination model 60 trained based on the slag removal operation of the dragger 31 by an experienced operator. This allows even an operator with a low level of skill to operate the dragger 31 and the vessel tilting unit 32 according to the operation parameters output from the parameter determination model 60, and also allows the operation of the dragger 31 and the vessel tilting unit 32 to be automatically controlled according to the operation parameters output from the parameter determination model 60.

[0053] Although the embodiments of the present disclosure have been described in detail above, the present disclosure is not limited to the specific embodiments described above, and various modifications and variations are possible within the scope of the gist of the present disclosure described in the claims. [Explanation of symbols]

[0054] 10. Slag removal system 20 containers 21 Slug 30 Slag remover 31 Dragger 32 Container tilting part 33 Scraping Board 40 Camera 50 Operation terminal 60 Parameter Determination Model 70 Training equipment 80 Training Data DB 100 Parameter determination device 110 Image acquisition unit 120 Parameter determination unit

Claims

1. an image acquisition unit for acquiring image data indicative of a surface of the molten metal in the vessel; a parameter determination unit that uses a parameter determination model to determine operational parameters of the slag remover, the operational parameters indicating the height of a slag remover and the tilt angle of the container for scraping off slag on the molten metal based on the image data; A parameter determining device having the following:

2. The parameter determination device according to claim 1 , wherein the parameter determination unit generates guidance information for operating the scraping machine based on the operational parameters and presents the guidance information to an operator.

3. The parameter determination device according to claim 1 , wherein the parameter determination unit outputs a control signal for the scraping machine based on the operating parameters.

4. 2. The parameter determination device of claim 1, wherein the parameter determination model is trained using training data consisting of image data showing a surface of the molten metal in the vessel and correct operation parameters showing the height of the slag removal member and the tilting angle of the vessel.

5. The parameter determination device according to claim 1 , wherein the parameter determiner generates surface area information that identifies a surface area of ​​the molten metal in the vessel.

6. The parameter determination device according to claim 5 , wherein the surface region information indicates a center position and a shape of an ellipse.

7. 7. The parameter determination apparatus of claim 6, wherein the parameter determination model is trained to determine the operational parameters indicative of a height of the slag removal member and a tilt angle of the vessel based on the surface area information.

8. 2. The parameter determination device according to claim 1, wherein the slag removal member is a scraping-type dragger having a scraping plate at a tip for scraping out the slag.

9. acquiring image data indicative of a surface of the molten metal within the vessel; determining operational parameters of a slag remover indicative of a height of a slag remover and a tilting angle of the vessel for scraping off slag on the molten metal based on the image data using a parameter determination model; 4. A computer implemented method for parameter determination comprising:

10. acquiring image data indicative of a surface of the molten metal within the vessel; determining operational parameters of a slag remover indicative of a height of a slag remover and a tilting angle of the vessel for scraping off slag on the molten metal based on the image data using a parameter determination model; A program that causes a computer to execute the following.

11. A data acquisition unit that acquires training data including image data showing a surface of the molten metal in the vessel and correct operation parameters showing a height of a slag removal member for scraping out slag on the molten metal and a tilting angle of the vessel; A training unit that uses the training data to train a parameter determination model; A training device having the above configuration.

12. acquiring image data indicative of a surface of the molten metal within the vessel; determining operational parameters of a slag remover indicative of a height of a slag removal member and a tilt angle of the vessel for scraping off slag above the molten metal based on the image data; A parameter determination model, A parameter determination model that is trained using training data consisting of image data showing the surface of the molten metal in the vessel and corrective operating parameters showing the height of a slag removal member for scraping off slag on the molten metal and the tilting angle of the vessel.

Citation Information

Patent Citations

  • Slag removing apparatus of melting furnace

    JP2018179348A

  • Melting operation device and melting operation method

    JP2019105389A

  • Automatic slag removal device and automatic slag removal program

    JP2020085395A