Visual judgment automatic argon blowing system and method for refining furnace

Abstract

The invention discloses a visual judgment automatic argon blowing system and method for a refining furnace. The visual judgment automatic argon blowing system comprises a camera, an instrument cabinet, an upper computer, an L2 system and a bottom argon blowing control cabinet. The instrument cabinet comprises a gigabit switch, a PLC (Programmable Logic Controller) and a human-computer interaction interface; the camera is connected with a first interface of the gigabit switch; a first interface of the PLC is connected with a second interface of the gigabit switch; the upper computer is connected with a third interface of the gigabit switch; a second interface of the PLC is connected with the L2 system; a third interface of the PLC is connected with the human-computer interaction interface; according to the bottom argon blowing control system, the operation efficiency of the refining furnace can be improved, the labor cost can be reduced, the product quality can be improved, the energy consumption can be reduced, and the bottom argon blowing control system has important significance on promoting the intelligent development of the industrial manufacturing field.

Description

Technical Field

[0001] The present invention relates to the technical field of refining furnace smelting, and more particularly to a visual determination automatic argon blowing system and method for a refining furnace. Background Art

[0002] The refining furnace is the main off-furnace refining equipment in steel production. During the refining process, the argon blowing pipe installed on the ladle is used to blow argon through the air-permeable bricks at the bottom to stir the molten steel in the ladle. Argon forms a large number of argon bubbles in the molten steel, which absorb and carry harmful gases in the molten steel. The gas dissolved in the molten steel will float to the surface of the molten steel with the bubbles and escape from the molten steel. The floating process of the argon bubbles will drive the stirring of the molten steel to discharge impurities, and at the same time accelerate the uniformity of the temperature and composition of the molten steel, so as to achieve the effect of accurately adjusting the composition of the molten steel.

[0003] At present, the argon blowing refining stirring flow rate regulation at home and abroad is all manually regulated, and the flow regulating valve is opened or closed manually according to the actual molten steel stirring intensity; therefore, there are also the following disadvantages: first, there is no quantitative indicator for the intensity itself, which is completely determined by manual judgment, and the control stability and accuracy are poor; second, the manual adjustment time is long, which affects the efficiency; third, the actual stirring effect is completely dependent on the standardized operation of people, and the reliability is not enough. It can be seen that the existing manually regulated argon blowing control scheme has poor control reliability, low stability, high labor intensity for workers, easy to affect the quality of molten steel, and will also increase the energy cost of argon gas.

[0004] Therefore, it is urgent to propose an automation technology with high efficiency, high control accuracy and good stability to solve the problems in the existing argon blowing and stirring. Summary of the invention

[0005] In view of this, the purpose of the present invention is to provide a visual judgment automatic argon blowing system and method for a refining furnace to solve the problems existing in the above-mentioned prior art.

[0006] To achieve the above object, the present invention provides the following technical solutions: A refining furnace visual judgment automatic argon blowing system, including a camera, an instrument cabinet, a host computer, an L2 system and a bottom argon blowing control cabinet; The instrument cabinet includes a gigabit switch, a PLC controller and a human-computer interaction interface; the PLC controller is electrically connected to the gigabit switch and the human-computer interaction interface respectively; The camera is connected to the Gigabit switch for communication; the Gigabit switch is connected to the host computer for communication; The PLC controller is electrically connected to the L2 system; The L2 system is electrically connected to the bottom blowing argon control cabinet; The camera is used to collect images of the distribution of molten steel and slag layer in the ladle liquid surface, and upload them to the host computer through the gigabit switch; The host computer includes an image processing module and a data management module; The image processing module is used to pre-process the image of the distribution of molten steel and slag layer in the ladle liquid surface, and calculate the proportion of the exposed area of ​​molten steel in the current ladle liquid surface based on image recognition technology; The data management module is established with expert model data, which is used to obtain the control target value of the bottom argon blowing control cabinet under the current stirring intensity from the expert model data, and determine the argon blowing control amount under the current stirring intensity according to the proportion of the exposed area of ​​molten steel in the current ladle liquid surface and the control target value; The PLC controller obtains the argon blowing control amount under the current stirring intensity and transmits it to the L2 system. The L2 system determines the argon blowing timing and argon blowing amount of the bottom argon blowing control cabinet to the ladle according to the argon blowing control amount; The L2 system uploads the basic information of the ladle and the argon blowing information to the host computer through the PLC controller.

[0007] Furthermore, the host computer also includes: a human-machine interface and an expert system module; The human-machine interface is used to display images of molten steel and slag in the ladle liquid surface and control information on argon gas flow in real time; The expert system module recognizes the image of the proportion of the molten steel area in the ladle liquid surface while the image processing module calculates the image of the proportion of the molten steel area in the ladle liquid surface in real time and the L2 system controls the argon blowing timing and argon blowing amount of the bottom argon blowing control cabinet, extracts the feature parameters corresponding to the current image, and saves the feature parameters of the current image in the expert model data.

[0008] Furthermore, the system is also provided with a camera protection device: the camera protection device includes a blowing and dust removal device; A slight positive pressure is formed in the camera protection device, and the camera is evenly purged by high-pressure gas through the tilt angle of the front pinhole lens, thereby achieving even purging of the camera.

[0009] Furthermore, the human-machine interaction interface and the human-machine interface are also used for the user to set manual control parameters to implement a manual mode.

[0010] Furthermore, the camera adopts an infrared camera, and the working parameters of the infrared camera are: the detection element is 640*480; the working wavelength is 8-14um; and the frame rate is 50Hz.

[0011] Furthermore, the human-computer interaction interface is specifically used to display the ladle liquid level image in real time, use different colors to represent molten steel and slag, and display the historical molten steel ratio changes through trend curves, play back historical videos in real time, and query the historical curves of molten steel area changes during argon blowing.

[0012] Furthermore, the expert model data includes: target ratio of exposed area of ​​molten steel under different stirring intensities, qualified ratio of exposed area of ​​molten steel, flow valve opening and flow range; The human-machine interaction interface is also provided with an automatic alarm function, which will give an alarm reminder when a fault occurs or the argon gas flow reaches the upper and lower limits; The processing time of the image processing module is within 50 ms.

[0013] Furthermore, the ladle information acquired by the L2 system is transmitted back to the system control module in real time, and the ladle information includes: ladle number, steel type, argon blowing start and argon flow rate.

[0014] The present invention also provides a method for visually determining an automatic argon blowing system of a refining furnace, the method comprising: a camera transmits an image of the distribution of molten steel and a slag layer in a ladle liquid surface to a host computer system and a PLC controller through a gigabit switch; the image of the distribution of molten steel and a slag layer in the ladle liquid surface is preprocessed by an image processing module in the host computer system, and the proportion of the exposed area of ​​molten steel in the current ladle liquid surface is calculated, and then the argon blowing control amount under the current stirring intensity is determined according to the proportion of the exposed area of ​​molten steel in the current ladle liquid surface and the control target value through the expert model data in the data management module, and at the same time, it is determined whether the ladle enters a predetermined position, when the ladle enters the predetermined position, the PLC controller obtains the argon blowing control amount under the current stirring intensity, and transmits it to the L2 system, the L2 system controls the flow regulating valve in the bottom argon blowing control cabinet to open according to the argon blowing control amount, and blows argon into the ladle; When the proportion of exposed molten steel area in the ladle liquid surface reaches the control target value, the L2 system controls the flow regulating valve in the bottom argon blowing control cabinet to close until the argon blowing is completed; The L2 system uploads the basic information of the ladle and the argon blowing information to the host computer through the PLC controller.

[0015] Furthermore, the image of the distribution of molten steel and slag layer in the ladle liquid surface is preprocessed, specifically: the features in the image of the distribution of molten steel and slag layer in the ladle liquid surface are preprocessed by one or more of increasing contrast and low-pass filtering, and then the proportion of the exposed area of ​​molten steel is calculated by one or more methods of binary method and color histogram; the contour information of the molten steel in the image is automatically extracted, the analysis area of ​​the image is determined, and the molten steel and slag layer are identified in the analysis area of ​​the image using automatic threshold segmentation technology.

[0016] The present invention also provides a method for automatic argon blowing of a refining furnace by visual judgment, the method comprising: a camera transmits an image of the distribution of molten steel and a slag layer in a ladle liquid surface to a host computer system and a PLC controller through a gigabit switch; the image of the distribution of molten steel and a slag layer in the ladle liquid surface is preprocessed by an image processing module in the host computer system, and the proportion of the exposed area of ​​molten steel in the current ladle liquid surface is calculated, and then the argon blowing control amount under the current stirring intensity is determined according to the proportion of the exposed area of ​​molten steel in the current ladle liquid surface and the control target value through the expert model data in the data management module, and at the same time, it is determined whether the ladle enters a predetermined position, when the ladle enters the predetermined position, the PLC controller obtains the argon blowing control amount under the current stirring intensity, and transmits it to the L2 system, the L2 system controls the flow regulating valve in the bottom argon blowing control cabinet to open according to the argon blowing control amount, and blows argon into the ladle; When the proportion of exposed molten steel area in the ladle liquid surface reaches the control target value, the L2 system controls the flow regulating valve in the bottom argon blowing control cabinet to close until the argon blowing is completed; The L2 system uploads the basic information of the ladle and the argon blowing information to the host computer through the PLC controller.

[0017] Furthermore, the image of the distribution of molten steel and slag layer in the ladle liquid surface is preprocessed, specifically: the features in the image of the distribution of molten steel and slag layer in the ladle liquid surface are preprocessed by one or more of increasing contrast and low-pass filtering, and then the proportion of the exposed area of ​​molten steel is calculated by one or more methods of binary method and color histogram; the contour information of the molten steel in the image is automatically extracted, the analysis area of ​​the image is determined, and the molten steel and slag layer are identified in the analysis area of ​​the image using automatic threshold segmentation technology.

[0018] According to the specific embodiment provided by the present invention, the present invention captures the smelting state in the ladle liquid surface in the refining furnace in real time, and accurately analyzes the image through the expert system module to determine the best time and amount of argon blowing. When the expert system module determines that argon blowing is required, it will automatically trigger the argon blowing device for precise control to ensure that the smelting process in the refining furnace reaches the optimal state. The implementation of the present invention can not only improve the operating efficiency of the refining furnace and reduce labor costs, but also improve product quality and reduce energy consumption, which is of great significance to promoting the intelligent development of the industrial manufacturing field. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0020] The following is a further description of the automatic argon blowing system and method for visual determination of a refining furnace according to the present invention in conjunction with the accompanying drawings; Figure 1 It is the overall structural diagram of the intelligent system of the bottom argon blowing device in the automatic argon blowing system of the refining furnace by visual judgment provided by the present invention; Figure 2 It is a schematic diagram of the area ratio of molten steel and slag in the automatic argon blowing system for visual determination of a refining furnace provided by the present invention; Figure 3 The radiation coefficient diagram of molten steel and slag in the automatic argon blowing system of the refining furnace provided by the present invention is provided; Figure 4 It is a system flow and process flow chart of the automatic argon blowing system for visual determination of a refining furnace provided by the present invention; In the figure: 1. Camera; 2. Instrument cabinet; 3. Gigabit switch; 4. PLC controller; 5. Human-computer interaction interface; 6. Host computer; 7. L2 system; 8. Bottom blowing argon control cabinet; 9. Ladle. DETAILED DESCRIPTION

[0021] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0022] In order to better understand the purpose, structure and function of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings.

[0023] like Figure 1 As shown, the present invention provides a refining furnace visual determination automatic argon blowing system, including a camera 1, an instrument cabinet 2, a host computer 6, an L2 system 7 and a bottom argon blowing control cabinet 8; The instrument cabinet 2 includes a gigabit switch 3, a PLC controller 4 and a human-machine interface 5; the PLC controller 4 is electrically connected to the gigabit switch 3 and the human-machine interface 5 respectively; The camera 1 is connected to the Gigabit switch 3 for communication; the Gigabit switch 3 is connected to the host computer 6 for communication; The PLC controller 4 is electrically connected to the L2 system 7; The L2 system 7 is electrically connected to the bottom blowing argon control cabinet 8; The camera 1 is used to collect images of the distribution of molten steel and slag layers in the liquid surface of the ladle 9, and upload them to the host computer 6 through the gigabit switch 3; The host computer 6 includes an image processing module and a data management module; The image processing module is used to pre-process the image of the distribution of the molten steel and the slag layer in the liquid surface of the ladle 9, and calculate the proportion of the exposed area of ​​the molten steel in the liquid surface of the ladle 9 based on the image recognition technology; The data management module is established with expert model data, which is used to obtain the control target value of the bottom argon blowing control cabinet 8 under the current stirring intensity from the expert model data, and determine the argon blowing control amount under the current stirring intensity according to the proportion of the exposed area of ​​molten steel in the current liquid level of the ladle 9 and the control target value; The PLC controller 4 obtains the argon blowing control amount under the current stirring intensity and transmits it to the L2 system 7. The L2 system 7 determines the argon blowing timing and argon blowing amount of the bottom argon blowing control cabinet 8 to the ladle 9 according to the argon blowing control amount; The L2 system 7 uploads the basic information of the ladle and the argon blowing information to the host computer 6 through the PLC controller 4.

[0024] The host computer also includes: a human-machine interface and an expert system module; The human-machine interface is used to display images of molten steel and slag in the ladle 9 in real time and control information on the argon gas flow rate; The expert system module recognizes the image of the proportion of the molten steel area in the liquid surface of the ladle 9 while the image processing module calculates the image of the proportion of the molten steel area in real time and the L2 system 7 controls the argon blowing timing and amount of the bottom argon blowing control cabinet 8, extracts the feature parameters corresponding to the current image, and saves the feature parameters of the current image in the expert model data.

[0025] The system is also provided with a camera protection device: the camera protection device includes a purge dust removal device and a temperature transmitter; A slight positive pressure is formed in the camera protection device, and the camera is evenly purged by high-pressure gas through the tilt angle of the front pinhole lens, so that the camera is evenly purged; The system also includes a temperature transmitter for monitoring the temperature in the camera protection device. When the temperature in the camera protection device exceeds a set value, an alarm is automatically sounded and a signal is sent to the PLC in the control box to execute extension and withdrawal.

[0026] The temperature transmitter is used to monitor the temperature in the camera protection device, and automatically alarms when the temperature in the camera protection device exceeds a set value.

[0027] The human-machine interaction interface 5 and the human-machine interface are also used for the user to set manual control parameters to implement the manual mode.

[0028] The camera 1 is an infrared camera, and the working parameters of the infrared camera are: the detection element is 640*480; the working wavelength is 8-14um; and the frame rate is 50Hz.

[0029] The human-computer interaction interface is specifically used to display the liquid level image of the ladle 9 in real time, use different colors to represent molten steel and slag, and display the historical changes in molten steel ratio through trend curves, play back historical videos in real time, and query the historical curves of molten steel area changes during argon blowing.

[0030] The expert model data includes: target ratio of exposed area of ​​molten steel under different stirring intensities, qualified ratio of exposed area of ​​molten steel, flow valve opening and flow range; The human-machine interaction interface is also provided with an automatic alarm function, which will give an alarm reminder when a fault occurs or the argon gas flow reaches the upper and lower limits; The processing time of the image processing module is within 50 ms.

[0031] The ladle 9 information acquired by the L2 system 7 is transmitted back to the system control module in real time. The ladle 9 information includes: ladle number, steel type, argon blowing start and argon flow rate.

[0032] The present invention further provides a method for automatic argon blowing by visual judgment of a refining furnace, the method comprising: a camera transmits an image of the distribution of molten steel and a slag layer in the liquid surface of a ladle 9 to a host computer system and a PLC controller through a gigabit switch; the image of the distribution of molten steel and a slag layer in the liquid surface of the ladle 9 is preprocessed by an image processing module in the host computer system, and the proportion of the exposed area of ​​molten steel in the liquid surface of the ladle 9 is calculated, and then the argon blowing control amount under the current stirring intensity is determined according to the proportion of the exposed area of ​​molten steel in the liquid surface of the ladle 9 and the control target value through the expert model data in the data management module, and at the same time, it is determined whether the ladle enters a predetermined position, when the ladle enters the predetermined position, the PLC controller 4) obtains the argon blowing control amount under the current stirring intensity, and transmits it to the L2 system 7, the L2 system 7 controls the flow regulating valve in the bottom argon blowing control cabinet 8 to open according to the argon blowing control amount, and blows argon into the ladle; When the proportion of the exposed area of ​​molten steel in the ladle 9 reaches the control target value, the L2 system controls the flow regulating valve in the bottom argon blowing control cabinet to close until the argon blowing is completed; The L2 system 7 uploads the basic information of the ladle and the argon blowing information to the host computer through the PLC controller 4.

[0033] The image of the distribution of the molten steel and the slag layer in the liquid surface of the ladle 9 is preprocessed, specifically: the features in the image of the distribution of the molten steel and the slag layer in the liquid surface of the ladle 9 are preprocessed by one or more of increasing contrast and low-pass filtering, and then the proportion of the exposed area of ​​the molten steel is calculated by one or more methods in the binary method and color histogram; the contour information of the molten steel in the image is automatically extracted, the analysis area of ​​the image is determined, and the molten steel and the slag layer are identified in the analysis area of ​​the image using automatic threshold segmentation technology.

[0034] It should be noted that the image processing module in the present invention adopts a proprietary optimized image processing technology, fully utilizes the parallel processing capability of a multi-core computer, and performs real-time analysis on the image of the camera 1, with the processing time controlled within 50ms.

[0035] Due to factors such as optical system distortion and atmospheric flow that may exist during video recording, the quality of the acquired image may be reduced. Therefore, it is necessary to use image augmentation technology to pre-process certain features of the captured image, enhance contrast, perform low-pass filtering, etc.; subsequently, the proportion of the exposed area of ​​molten steel is calculated through methods such as binarization and color histogram.

[0036] After the image is collected, filtering is performed to automatically extract the contour information of the molten steel in the image, determine the analysis area of ​​the image, and use automatic threshold segmentation technology to identify the molten steel and slag.

[0037] The host computer 6 is equipped with a synchronous display in the operation room and a corresponding integrated display and operation screen outdoors to display the liquid level image in the iron ladle in real time so that the operator can monitor the entire process more intuitively. Different colors are used to represent molten steel and slag, and trend curves are used to display historical changes in molten steel ratios. Users can also play back historical videos in real time and query historical curves to analyze changes in molten steel area during argon blowing.

[0038] The image processing process of the present invention includes an efficient image processing algorithm and has the following characteristics: (1) Image acquisition, filtering, and extraction of image contour information; (2) Determine the analysis area; (3) Apply threshold segmentation technology to the analysis area to automatically identify molten steel and slag; (4) Identify the characteristics of steel slag and prevent interference caused by factors such as flames and liquid surface rolling during argon blowing; (5) Color processing: molten steel and slag are contrasted by using different colors.

[0039] The working parameters of the camera 1 are: the detection element is 640*480; the working wavelength is 8-14um; the frame rate is 50Hz; and the maximum temperature measurement is 2000°C.

[0040] The color processing of the distribution of molten steel and slag layer in the ladle liquid surface is specifically as follows: certain features in the image are preprocessed by one or more of increasing contrast and low-pass filtering, and then the proportion of the molten steel area is calculated by one or more methods of binary method and color histogram; the contour information of the molten steel in the image is automatically extracted, the analysis area of ​​the image is determined, and the molten steel and slag layer are identified in the analysis area of ​​the image by using automatic threshold segmentation technology.

[0041] The human-machine interface is specifically used to display the ladle liquid level image in real time, use different colors to represent molten steel and slag, and display the historical molten steel ratio changes through trend curves. It can also play back historical videos in real time and query the historical curves of molten steel area changes during argon blowing.

[0042] The data management module also stores a standard database, which includes the target ratio of exposed area of ​​molten steel under different stirring intensities, the qualified ratio of exposed area of ​​molten steel, the flow valve opening and the flow range. After the image processing module calculates the exposed area ratio of molten steel, the corresponding argon blowing control amount is obtained according to the control target value under the current stirring intensity.

[0043] A standard database is established, i.e., the target ratio of exposed steel area under various stirring intensities, the qualified ratio of exposed steel area, flow valve opening, flow range and other data constants. These parameters can be viewed and modified online in the software. After the image recognition function calculates the exposed steel area ratio, the corresponding control quantity is obtained from a set of expert data models according to the control target value under the current stirring intensity.

[0044] Data management mainly completes the storage and query of field application results and the preservation of weak stirring images. The performance data is stored in the SQL SERVER database by using the furnace as the index to establish a data table, and the historical performance can be queried by furnace in the future; and the weak stirring image is saved in the computer hard disk in the form of a picture.

[0045] Expert system module: As the application of artificial intelligence in various industries gradually deepens, intelligent systems need to have a re-learning function. As mentioned above, automatic argon blowing of molten steel is an intelligent system based on image recognition. The image comes from the actual on-site working conditions. Whether the image features can be correctly matched with the actual state is the core of the present invention. Therefore, while performing image recognition and control output, the system software can recognize some images of known results, extract the feature parameters corresponding to the current image, and save these parameters in the expert model data to form an expert system with deep learning function.

[0046] Data communication module: (1) Obtain information transmitted from the secondary system of the steel plant, such as ladle number, steel type, argon blowing start, argon flow rate, etc.; (2) Information transmitted back to the secondary system of the steel plant: argon blowing control permission, argon flow rate increase or decrease, etc.; (3) Obtain furnace information from steelmaking L2 and transmit the processing results back to the steelmaking L2 system. (Upper computer) Human-machine interface, with the following features: (1) A liquid crystal display is installed in the operating room. The main screen includes an image area for real-time display of the current molten steel and slag images. The operator can observe the changes in the molten steel area of ​​the ladle during the argon blowing process through the display in real time; (2) During the automatic control process, the operation screen prompts the ongoing operation, such as increasing or decreasing the argon gas flow rate.

[0047] (3) Equipped with an alarm function, when a system failure occurs, such as when the argon gas flow rate reaches the upper and lower limits, prompts processing.

[0048] The system of the present invention also has the following technical effects: a. Automatically confirm whether the ladle is in place; b. The camera lens protection device has the design requirements of shock resistance, dust resistance and high temperature resistance; c. Image transmission has anti-electromagnetic interference processing to avoid clutter interference during image transmission; d. Realize communication function with the existing secondary system of the steel plant; e. The system can display in color, distinguish molten steel and slag with distinct colors, and make color transition effect according to the thickness of slag layer. Operators can clearly distinguish the distribution of slag by looking at the color effect diagram; f. The system can calculate the proportion of molten steel area in the ladle liquid surface in real time, and automatically adjust the argon flow rate according to the set percentage; g. Monitor the changes in the molten steel area of ​​the ladle during the argon blowing process in real time and automatically realize the real-time video recording function; h. Configure a synchronous real-time display screen in the operation room for operators to observe the changes of molten iron and slag in the ladle in real time; i. The system can realize manual / automatic free switching of argon blowing control; j. Realize the historical data query function. The operator can query the historical data according to the key information such as ladle number, argon blowing time, steel type, etc. After selecting the query conditions, the system automatically loads the corresponding slag removal historical video, historical curve, etc.; the system has the function of automatically deleting historical data, and the historical data retention period can be set.

[0049] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A visual judgment automatic argon blowing system for a refining furnace, characterized in that: It includes a camera (1), an instrument cabinet (2), a host computer (6), an L2 system (7) and a bottom blowing argon control cabinet (8); The instrument cabinet (2) comprises a gigabit switch (3), a PLC controller (4) and a human-machine interaction interface (5); the PLC controller (4) is electrically connected to the gigabit switch (3) and the human-machine interaction interface (5) respectively; The camera (1) is connected to a gigabit switch (3) for communication; the gigabit switch (3) is connected to a host computer (6) for communication; The PLC controller (4) is electrically connected to the L2 system (7); The L2 system (7) is electrically connected to the bottom blowing argon control cabinet (8); The camera (1) is used to collect images of the distribution of molten steel and slag layers in the liquid surface of the ladle (9), and upload the images to the host computer (6) via the gigabit switch (3); The host computer (6) includes an image processing module and a data management module; The image processing module is used to pre-process an image of the distribution of the molten steel and the slag layer on the liquid surface of the ladle (9), and calculate the proportion of the exposed area of ​​the molten steel on the liquid surface of the ladle (9) based on image recognition technology; The data management module is established with expert model data, which is used to obtain the control target value of the bottom argon blowing control cabinet (8) under the current stirring intensity from the expert model data, and determine the argon blowing control amount under the current stirring intensity according to the proportion of the exposed area of ​​molten steel in the liquid surface of the current ladle (9) and the control target value; The PLC controller (4) obtains the argon blowing control amount under the current stirring intensity and transmits it to the L2 system (7); the L2 system (7) determines the timing and amount of argon blowing by the bottom argon blowing control cabinet (8) to the ladle (9) according to the argon blowing control amount; The L2 system (7) uploads the basic information of the ladle and the argon blowing information to the host computer (6) through the PLC controller (4).

2. The automatic argon blowing system for refining furnace visual determination according to claim 1 is characterized in that: The host computer also includes: a human-machine interface and an expert system module; The human-machine interface is used to display images of molten steel and slag in the liquid surface of the ladle (9) and control information on the argon gas flow in real time; The expert system module recognizes the image of the proportion of the molten steel area in the liquid surface of the ladle (9) while the image processing module calculates in real time the image of the proportion of the molten steel area in the liquid surface of the ladle (9) and the L2 system (7) controls the argon blowing timing and argon blowing amount of the bottom argon blowing control cabinet (8), extracts feature parameters corresponding to the current image, and stores the feature parameters of the current image in the expert model data.

3. The automatic argon blowing system for refining furnace visual determination according to claim 1, characterized in that: The system is also provided with a camera protection device: the camera protection device includes a blowing and dust removal device; A slight positive pressure is formed in the camera protection device, and the camera is evenly purged by high-pressure gas through the tilt angle of the front pinhole lens, thereby achieving even purging of the camera.

4. The automatic argon blowing system for refining furnace visual determination according to claim 1, characterized in that: The human-machine interaction interface (5) and the human-machine interface are also used for the user to set manual control parameters to implement a manual mode.

5. The automatic argon blowing system for refining furnace visual determination according to claim 1, characterized in that: The camera (1) is an infrared camera, and the working parameters of the infrared camera are: the detection element is 640*480; the working wavelength is 8-14um; and the frame rate is 50Hz.

6. The automatic argon blowing system for refining furnace visual determination according to claim 1, characterized in that: The human-computer interaction interface is specifically used for real-time display of the steel ladle (9) liquid level image, using different colors to represent molten steel and slag, and displaying historical molten steel ratio changes through trend curves, real-time playback of historical videos, and querying historical curves of molten steel area changes during argon blowing.

7. The automatic argon blowing system for refining furnace visual determination according to claim 1, characterized in that: The expert model data includes: target ratio of exposed area of ​​molten steel under different stirring intensities, qualified ratio of exposed area of ​​molten steel, flow valve opening and flow range; The human-machine interaction interface is also provided with an automatic alarm function, which will give an alarm reminder when a fault occurs or the argon gas flow reaches the upper and lower limits; The processing time of the image processing module is within 50 ms.

8. The automatic argon blowing system for refining furnace visual determination according to claim 1, characterized in that: The ladle (9) information acquired by the L2 system (7) is transmitted back to the system control module in real time, and the ladle (9) information includes: ladle number, steel type, argon blowing start, and argon gas flow rate.

9. A method for visually determining an automatic argon blowing system for a refining furnace, applied to the visually determining automatic argon blowing system for a refining furnace as claimed in any one of claims 1 to 8, characterized in that: The method comprises: a camera (1) transmits an image of the distribution of molten steel and a slag layer on the surface of a ladle (9) to a host computer system and a PLC controller via a gigabit switch; preprocessing the image of the distribution of molten steel and a slag layer on the surface of the ladle (9) via an image processing module in the host computer system, and calculating the proportion of the exposed area of ​​molten steel on the surface of the ladle (9) at present, and then determining the argon blowing control amount under the current stirring intensity according to the proportion of the exposed area of ​​molten steel on the surface of the ladle (9) and a control target value through expert model data in a data management module, and judging whether the ladle has entered a predetermined position at the same time; when the ladle has entered the predetermined position, the PLC controller (4) obtains the argon blowing control amount under the current stirring intensity and transmits it to the L2 system (7); the L2 system (7) controls the flow regulating valve in the bottom argon blowing control cabinet (8) to open according to the argon blowing control amount, and blows argon into the ladle; When the proportion of the exposed area of ​​molten steel in the liquid surface of the ladle (9) reaches the control target value, the L2 system controls the flow regulating valve in the bottom argon blowing control cabinet to close until the argon blowing is completed; The L2 system (7) uploads the basic information of the ladle and the argon blowing information to the host computer through the PLC controller (4).

10. The method for visually determining the automatic argon blowing system of a refining furnace according to claim 9, characterized in that: The image of the distribution of the molten steel and the slag layer on the liquid surface of the ladle (9) is preprocessed, specifically: the features in the image of the distribution of the molten steel and the slag layer on the liquid surface of the ladle (9) are preprocessed by one or more of increasing contrast and low-pass filtering, and then the proportion of the exposed area of ​​the molten steel is calculated by one or more of the binary method and the color histogram method; the contour information of the molten steel in the image is automatically extracted, the analysis area of ​​the image is determined, and the molten steel and the slag layer are identified in the analysis area of ​​the image using an automatic threshold segmentation technology.

Images