Converter bottom blowing efficient control method and device based on machine vision

Abstract

This invention discloses a machine vision-based method and device for efficient control of converter bottom blowing, belonging to the field of converter steelmaking technology. The method includes: constructing a historical heat data database; establishing a converter model for the blowing process and simulating the converter bottom blowing process to obtain the converter bottom blowing flow rate corresponding to the optimal flow field at each time period under various combination conditions; performing online real-time detection of data information from each branch of bottom blowing; visually detecting the state characteristics of the permeable elements in each branch of bottom blowing during the tapping process; using the converter model for the blowing process to perform system analysis, calculation, adjustment, and correction of the real-time detection data and visual detection data to obtain the correction value for the flow control of each branch of bottom blowing on the time axis under the conditions of this heat; and feeding back the correction value and relevant data information of this heat to the historical heat data database for model self-learning. This invention achieves efficient control of converter bottom blowing based on machine vision, with significant economic benefits and broad prospects for application.

Description

Technical Field

[0001] This invention relates to a machine vision-based method and device for efficient control of bottom blowing in converters, belonging to the field of converter steelmaking technology. Background Technology

[0002] After decades of experimentation and practice, the top-bottom combined blowing process has become basically mature. In this process, O2 is blown from the top of the converter and inert gas is blown from the bottom to uniformly stir the molten pool, bringing the reaction in the molten pool closer to equilibrium. This not only improves the quality of molten steel and reduces the cost per ton of steel, but also increases the flexibility and adaptability of the converter and enhances its ability to melt scrap steel. As a result, the amount of scrap steel fed into the furnace can be flexibly adjusted according to changes in market scrap steel and molten iron prices, thereby achieving economic benefits.

[0003] The converter bottom-blowing gas sources include various types such as N2, Ar, O2, and CO2, and the bottom-blowing gas supply elements are also diversified. Through improvements in the materials, molding processes, structures, and protective bricks of the gas supply elements, as well as optimization of the converter bottom lining process, re-blowing process, and maintenance system, the lifespan of the converter re-blowing system has been significantly improved. Under top-bottom re-blowing conditions, the uniform mixing time decreases with increasing top-blowing gas penetration depth and bottom-gas ratio. Increasing the bottom-blowing flow rate increases the stirring energy of the molten pool, thus reducing the uniform mixing time. Therefore, appropriately increasing the bottom-blowing gas supply intensity is beneficial for improving the bottom-blowing stirring effect of the converter. However, excessively high bottom-blowing gas supply intensity will also shorten the lifespan of the bottom-blowing gas supply elements.

[0004] The charging conditions and specific operations of converter blowing furnaces vary greatly, and process control is highly variable. The effectiveness of converter bottom blowing involves a series of factors, including the charging system, slagging system, oxygen supply system, temperature system, deoxidation and alloying, oxygen lance position control, blowing endpoint temperature and carbon content, refractory life, bottom blowing element life and maintenance status, and real-time status monitoring of bottom blowing elements. It also involves numerous technical, equipment, and management issues, depending on the parameter design of the top and bottom combined blowing process, the availability of raw materials, the standardization of operating procedures, the steel grade being smelted, and the smelting process conditions, especially the condition maintenance and functional assurance of equipment components. Without the functional assurance and basic conditions of the bottom blowing elements, even the best simulation and optimization measures and effects cannot be realized. Summary of the Invention

[0005] To address the aforementioned problems, this invention proposes a machine vision-based method and device for efficient control of converter bottom blowing, which enables precise and efficient control of the bottom blowing effect.

[0006] The technical solution adopted by this invention to solve its technical problem is as follows:

[0007] In a first aspect, the present invention provides a machine vision-based high-efficiency control method for converter bottom blowing, comprising the following steps:

[0008] Step S1: Collect historical furnace information and build a historical furnace data information database;

[0009] Step S2: Establish a converter model for the blowing process and use Fluent finite element simulation analysis software to simulate the converter bottom blowing process, and obtain the converter bottom blowing flow rate corresponding to the optimal flow field for each time period under various combination conditions.

[0010] Step S3: Real-time online monitoring of the data information of each branch of bottom blowing, and timely input into the converter model of the blowing process for tracking, analysis and judgment. The data information of each branch of bottom blowing includes the flow rate, pressure and deviation from the set value of each branch of bottom blowing.

[0011] Step S4: Visually detect the status characteristics of the ventilation elements in each branch of the bottom blowing process during the steel tapping process;

[0012] Step S5: The real-time monitored data of each branch of bottom blowing and the visually monitored state characteristic data of the permeable elements of each branch of bottom blowing during the tapping process are used to perform system analysis, calculation, adjustment and correction using the converter model of the blowing process, to obtain the correction value F of the flow control of each branch of bottom blowing on the time axis under the conditions of this heat. t-i-修正 i is the bottom blowing branch number;

[0013] Step S6, adjust the value F t-i-修正 The data and related information of this furnace are fed back to the historical furnace data information database for model self-learning.

[0014] As one possible implementation of this embodiment, the historical furnace information includes at least the following: molten iron charging conditions, scrap steel conditions, slag-forming auxiliary materials, target steel grade, oxygen consumption, endpoint conditions, control curves, and furnace lining refractory life. The molten iron charging conditions include the composition, temperature, and weight of the molten iron; the scrap steel conditions include the type and weight of the scrap steel; the slag-forming auxiliary materials include the composition and amount of the slag-forming auxiliary materials added; the target steel grade includes the composition, temperature, final slag composition, and basicity requirements of the target steel grade; the endpoint conditions include the endpoint composition and temperature; and the control curves include the temperature control curve for the blowing process, the oxygen lance position control curve, and the control curves for each branch of the converter bottom blowing.

[0015] As one possible implementation of this embodiment, step S2 involves establishing a converter model for the blowing process and using Fluent finite element simulation software to simulate the converter bottom blowing process, obtaining the converter bottom blowing flow rate corresponding to the optimal flow field for each time period under various combination conditions, including:

[0016] The raw data of historical furnaces are classified, analyzed and combined according to the same or similar principles to establish a secondary database of various combination types under the same or similar conditions;

[0017] A converter model for the blowing process was established, and for each combination type in the secondary database, the bottom blowing process of the converter was simulated using Fluent finite element simulation analysis software to obtain the converter bottom blowing flow rate corresponding to the optimal flow field at each time period under various combination types.

[0018] As one possible implementation of this embodiment, the step of establishing a converter model for the blowing process, and using Fluent finite element simulation analysis software to simulate the converter bottom blowing process for each combination type in the secondary database, obtains the converter bottom blowing flow rate corresponding to the optimal flow field for each time period under various combination types, including:

[0019] A converter model for the blowing process was built using SolidWorks software.

[0020] The bottom blowing process of the converter was simulated using Fluent finite element simulation analysis software for each combination type in the secondary database.

[0021] Analyze the velocity vector diagram of the gas-liquid-solid circulation flow in the converter pool under the action of top and bottom blowing under various combination types;

[0022] Comparative analysis yielded the converter bottom blowing flow rates corresponding to the optimal flow fields at different time periods under various combination conditions. It also yielded the optimal flow rate values ​​F for each branch of the bottom blowing system at different time periods when the molten steel circulates in the molten pool under the action of bottom blowing gas, corresponding to the optimal flow fields. t-i-模拟 i represents the bottom blowing branch number. The various combination conditions include the specific furnace base size, bottom blowing element type and location arrangement, quantity number, and poor permeability or blockage of individual branches.

[0023] As one possible implementation of this embodiment, step S4, which involves visually detecting the state characteristics of the ventilation elements in each branch of the bottom blowing process during steel tapping, includes:

[0024] During the tapping process, after the converter tilts to the tapping position, the state characteristics of the bottom blowing elements distributed at the bottom of the furnace are photographed.

[0025] After image recognition of the captured images, they are input into the converter model of the blowing process and compared with the corresponding images of historical furnaces to determine the status trend.

[0026] As one possible implementation of this embodiment, in step S5, when the online real-time monitoring of the flow rate of each branch of the bottom blowing process shows that the flow rate of a certain branch increases while the pressure decreases, it indicates that the venting element has a tendency to be more severely eroded. The converter model of the blowing process adjusts and reduces the corresponding flow rate of the branch through calculation. Conversely, if the flow rate decreases while the pressure increases, it indicates a tendency to be blocked. The converter model of the blowing process appropriately increases the flow rate of the branch through calculation.

[0027] Similarly, when the visual detection, comparison, and judgment of the status characteristics of the permeable elements in each branch of the bottom blowing process are performed, if a certain element shows an increase in the permeable area and a thinning of the slag layer covering the permeable element, it indicates that the erosion of that branch is intensifying. The converter model in the blowing process will correspondingly reduce the flow rate of that branch to avoid the continued aggravation of this state, which could lead to the scrapping of the element or even a steel leakage accident. Conversely, if a certain branch shows a gradual decrease in the permeable area and a thickening of the slag layer covering the permeable element, it indicates that the branch is showing a tendency to blockage. The converter model in the blowing process will also automatically adjust and increase the flow rate to avoid blockage.

[0028] As one possible implementation of this embodiment, the machine vision-based converter bottom blowing high-efficiency control method further includes the following steps:

[0029] Step S7: Use a dedicated maintenance device to perform online maintenance on the ventilation elements of each branch of the bottom blowing system;

[0030] The specialized maintenance device includes a nozzle, a gun body, a cooling water pipe, a jetting pipe, a cooling water inlet, a cooling water outlet, a switching valve, an oxygen interface, a spraying interface, and a support frame. The gun body consists of a cooling water pipe and a jetting pipe installed inside the cooling water pipe. The nozzle is located at the front end of the gun body, and the switching valve is located at the rear end. The jetting pipe is connected to the oxygen interface or the spraying interface through the switching valve. The cooling water pipe is equipped with a cooling water inlet and a cooling water outlet. The gun body is mounted on the support frame, and the nozzle extends, retracts, and rotates within the converter.

[0031] When a branch shows an increasing trend of erosion, the branch is sprayed and maintained during the production break. The special maintenance device is switched to the spraying state, and the evenly mixed spraying material and water are sprayed onto the component area of ​​the branch for spraying and sintering to make up for the eroded slag layer on the upper part of the component and increase the thickness of the slag layer.

[0032] When a branch component shows signs of blockage, the same "rinsing" treatment is carried out on the branch component during the production interval. At this time, the function of the special maintenance device is switched to the "rinsing" state, and oxygen is injected to "rinse" the excessively thick slag layer in the component area, thinning the covering slag layer, ensuring the air permeability of the bottom blowing component and avoiding blockage.

[0033] Secondly, an embodiment of the present invention provides a high-efficiency control device for converter bottom blowing based on machine vision, comprising:

[0034] The historical furnace data information database establishment module is used to collect historical furnace information and build a historical furnace data information database.

[0035] The converter bottom blowing process simulation module is used to establish a converter model of the blowing process and use Fluent finite element simulation analysis software to simulate the converter bottom blowing process, and obtain the converter bottom blowing flow rate corresponding to the optimal flow field at each time period under various combination conditions.

[0036] The bottom blowing branch real-time detection module is used to detect the data information of each bottom blowing branch online in real time, and input it into the converter model of the blowing process in a timely manner for tracking, analysis and judgment. The data information of each bottom blowing branch includes the flow rate, pressure and deviation from the set value of each bottom blowing branch.

[0037] The visualization detection module is used to visualize and detect the status characteristics of the ventilation elements in each branch of the bottom blowing process during the steel tapping process.

[0038] The adjustment and correction module is used to analyze, calculate, adjust, and correct the real-time monitoring data of each branch of bottom blowing and the visual monitoring data of the permeability elements of each branch of bottom blowing during the tapping process using a converter model of the blowing process, so as to obtain the correction value F of the flow control of each branch of bottom blowing on the time axis under the conditions of this heat. t-i-修正 i is the bottom blowing branch number;

[0039] The model self-learning module is used to adjust the value F. t-i-修正 The data and related information of this furnace are fed back to the historical furnace data information database for model self-learning.

[0040] As one possible implementation of this embodiment, the machine vision-based converter bottom blowing high-efficiency control device further includes:

[0041] The online maintenance module for ventilated elements is used to perform online maintenance on the ventilated elements of each branch of the bottom blowing system using a dedicated maintenance device.

[0042] Thirdly, an electronic device provided by an embodiment of the present invention includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus, and the processor executes the machine-readable instructions to perform the steps of any of the machine vision-based converter bottom blowing high-efficiency control methods described above.

[0043] Fourthly, embodiments of the present invention provide a storage medium storing a computer program, which, when executed by a processor, performs the steps of any of the machine vision-based converter bottom blowing high-efficiency control methods described above.

[0044] The beneficial effects of the technical solutions of the embodiments of the present invention are as follows:

[0045] This invention constructs a model based on current production process conditions and equipment parameters, collects, analyzes, and classifies historical data, and performs numerical simulation analysis in conjunction with bottom blowing process conditions to obtain the optimal parameters under various process conditions. Then, it adjusts the parameters according to the specific actual conditions of the current furnace, and optimizes and corrects them by combining the visual detection results of bottom blowing elements. The model is then re-analyzed and calculated to obtain adjustment information and guiding maintenance measures, thereby achieving precise and efficient control of the bottom blowing effect.

[0046] This invention classifies, analyzes, and combines historical data under similar or identical conditions, and performs simulation analysis of bottom blowing processes under various combinations. This yields the optimal flow rate F for each branch of the bottom blowing process at different time periods, corresponding to the optimal flow field of the molten steel circulating in the molten pool under the action of bottom blowing gas under various combinations. t-i-模拟 By combining "online real-time monitoring of the flow rate of each branch of bottom blowing" and "visual detection of the status characteristics of the permeable elements of each branch of bottom blowing during the tapping process," model calculations, analysis, adjustments, and corrections were performed to obtain the correction value F for the flow rate control of each branch of bottom blowing on the time axis under the conditions of this heat. t-i-修正 Meanwhile, the timely online maintenance of the bottom blowing elements through a dedicated device greatly improves the lifespan and reblowing effect of the bottom blowing elements, enhances steel quality and production efficiency, reduces process production costs and system maintenance intensity, and achieves efficient control of converter bottom blowing based on machine vision, which has significant economic benefits and broad prospects for promotion. Attached Figure Description

[0047] Figure 1 This is a flowchart illustrating a machine vision-based efficient control method for bottom blowing in a converter, according to an exemplary embodiment.

[0048] Figure 2 This is a schematic diagram of the structure of a machine vision-based high-efficiency control device for bottom blowing in a converter, according to an exemplary embodiment.

[0049] Figure 3 This is a schematic diagram of a dedicated maintenance device structure according to an exemplary embodiment;

[0050] Figure 4 This is a schematic diagram of online maintenance of bottom blowing components using a dedicated maintenance device;

[0051] Figure 5 This is a flowchart of efficient control of converter bottom blowing based on machine vision using the machine vision-based converter bottom blowing high-efficiency control device described in this invention.

[0052] Figure 6 The corrected control curve F for the bottom blowing branch #2 flow rate on the time axis under the specific conditions of furnace batch 1 in Example 1 is obtained. t-i-修正 Schematic diagram;

[0053] Figure 7 The corrected control curve F for the flow rate of the bottom blowing branch #2 on the time axis under the specific conditions of furnace batch 2 in example 2 is obtained. t-i-修正 Schematic diagram. Detailed Implementation

[0054] To more clearly illustrate the technical features of the present invention, the present invention will be described in detail below through specific embodiments and in conjunction with the accompanying drawings.

[0055] Efficient bottom blowing control in converters involves numerous technical, equipment, and management issues. It requires comprehensive consideration of multiple factors. By using visual monitoring, standardized operation, and online maintenance, coupled and coordinated with various historical data and real-time process detection data for model calculation and regulation, the control level and reblowing effect can be significantly improved, thereby further improving the quality of molten steel and production efficiency.

[0056] like Figure 1 As shown in the figure, an embodiment of the present invention provides a high-efficiency control method for converter bottom blowing based on machine vision, comprising the following steps:

[0057] Step S1: Collect historical furnace information and build a historical furnace data information database;

[0058] Step S2: Establish a converter model for the blowing process and use Fluent finite element simulation analysis software to simulate the converter bottom blowing process, and obtain the converter bottom blowing flow rate corresponding to the optimal flow field for each time period under various combination conditions.

[0059] Step S3: Real-time online monitoring of the data information of each branch of bottom blowing, and timely input into the converter model of the blowing process for tracking, analysis and judgment. The data information of each branch of bottom blowing includes the flow rate, pressure and deviation from the set value of each branch of bottom blowing.

[0060] Step S4: Visually detect the status characteristics of the ventilation elements in each branch of the bottom blowing process during the steel tapping process;

[0061] Step S5: The real-time monitored data of each branch of bottom blowing and the visually monitored state characteristic data of the permeable elements of each branch of bottom blowing during the tapping process are used to perform system analysis, calculation, adjustment and correction using the converter model of the blowing process, to obtain the correction value F of the flow control of each branch of bottom blowing on the time axis under the conditions of this heat. t-i-修正 i is the bottom blowing branch number;

[0062] Step S6, adjust the value F t-i-修正 The data and related information of this furnace are fed back to the historical furnace data information database for model self-learning.

[0063] As one possible implementation of this embodiment, the historical furnace information includes at least the following: molten iron charging conditions, scrap steel conditions, slag-forming auxiliary materials, target steel grade, oxygen consumption, endpoint conditions, control curves, and furnace lining refractory life. The molten iron charging conditions include the composition, temperature, and weight of the molten iron; the scrap steel conditions include the type and weight of the scrap steel; the slag-forming auxiliary materials include the composition and amount of the slag-forming auxiliary materials added; the target steel grade includes the composition, temperature, final slag composition, and basicity requirements of the target steel grade; the endpoint conditions include the endpoint composition and temperature; and the control curves include the temperature control curve for the blowing process, the oxygen lance position control curve, and the control curves for each branch of the converter bottom blowing.

[0064] As one possible implementation of this embodiment, step S2 involves establishing a converter model for the blowing process and using Fluent finite element simulation software to simulate the converter bottom blowing process, obtaining the converter bottom blowing flow rate corresponding to the optimal flow field for each time period under various combination conditions, including:

[0065] The raw data of historical furnaces are classified, analyzed and combined according to the same or similar principles to establish a secondary database of various combination types under the same or similar conditions;

[0066] A converter model for the blowing process was established, and for each combination type in the secondary database, the bottom blowing process of the converter was simulated using Fluent finite element simulation analysis software to obtain the converter bottom blowing flow rate corresponding to the optimal flow field at each time period under various combination types.

[0067] As one possible implementation of this embodiment, the step of establishing a converter model for the blowing process, and using Fluent finite element simulation analysis software to simulate the converter bottom blowing process for each combination type in the secondary database, obtains the converter bottom blowing flow rate corresponding to the optimal flow field for each time period under various combination types, including:

[0068] A converter model for the blowing process was built using SolidWorks software.

[0069] The bottom blowing process of the converter was simulated using Fluent finite element simulation analysis software for each combination type in the secondary database.

[0070] Analyze the velocity vector diagram of the gas-liquid-solid circulation flow in the converter pool under the action of top and bottom blowing under various combination types;

[0071] Comparative analysis yielded the converter bottom blowing flow rates corresponding to the optimal flow fields at different time periods under various combination conditions. It also yielded the optimal flow rate values ​​F for each branch of the bottom blowing system at different time periods when the molten steel circulates in the molten pool under the action of bottom blowing gas, corresponding to the optimal flow fields. t-i-模拟i represents the bottom blowing branch number. The various combination conditions include the specific furnace base size, bottom blowing element type and location arrangement, quantity number, and poor permeability or blockage of individual branches.

[0072] As one possible implementation of this embodiment, step S4, which involves visually detecting the state characteristics of the ventilation elements in each branch of the bottom blowing process during steel tapping, includes:

[0073] During the tapping process, after the converter tilts to the tapping position, the state characteristics of the bottom blowing elements distributed at the bottom of the furnace are photographed.

[0074] After image recognition of the captured images, they are input into the converter model of the blowing process and compared with the corresponding images of historical furnaces to determine the status trend.

[0075] As one possible implementation of this embodiment, in step S5, when the online real-time monitoring of the flow rate of each branch of the bottom blowing process shows that the flow rate of a certain branch increases while the pressure decreases, it indicates that the venting element has a tendency to be more severely eroded. The converter model of the blowing process adjusts and reduces the corresponding flow rate of the branch through calculation. Conversely, if the flow rate decreases while the pressure increases, it indicates a tendency to be blocked. The converter model of the blowing process appropriately increases the flow rate of the branch through calculation.

[0076] Similarly, when the visual detection, comparison, and judgment of the status characteristics of the permeable elements in each branch of the bottom blowing process are performed, if a certain element shows an increase in the permeable area and a thinning of the slag layer covering the permeable element, it indicates that the erosion of that branch is intensifying. The converter model in the blowing process will correspondingly reduce the flow rate of that branch to avoid the continued aggravation of this state, which could lead to the scrapping of the element or even a steel leakage accident. Conversely, if a certain branch shows a gradual decrease in the permeable area and a thickening of the slag layer covering the permeable element, it indicates that the branch is showing a tendency to blockage. The converter model in the blowing process will also automatically adjust and increase the flow rate to avoid blockage.

[0077] As one possible implementation of this embodiment, the machine vision-based converter bottom blowing high-efficiency control method further includes the following steps:

[0078] Step S7: Use a dedicated maintenance device to perform online maintenance on the ventilation elements of each branch of the bottom blowing system;

[0079] like Figure 2As shown, the special maintenance device includes a nozzle 1, a gun body 2, a cooling water pipe 3, a jetting pipe 4, a cooling water inlet 5, a cooling water outlet 6, a switching valve 7, an oxygen interface 8, a spraying interface 9, and a support frame 10. The gun body 2 is composed of a cooling water pipe 3 and a jetting pipe 4 installed inside the cooling water pipe. The nozzle 1 is located at the front end of the gun body 2, and the switching valve 7 is located at the rear end. The jetting pipe 2 is connected to the oxygen interface 8 or the spraying interface 9 through the switching valve 7. The cooling water pipe 3 is provided with a cooling water inlet 5 and a cooling water outlet 6. The gun body 1 is mounted on the support frame 10, and the nozzle extends, retracts, and rotates inside the converter.

[0080] When a branch road shows signs of erosion worsening, spray maintenance is performed on that branch road during production breaks, such as... Figure 4 As shown, Figure 4 In the diagram, 11 represents the converter; 12 represents the converter opening; and 13 represents the tapping port. The gun body of the maintenance device is placed inside the converter through the converter opening. The special maintenance device is switched to the spraying state, i.e., the switching valve is adjusted to connect the spraying pipe to the spraying interface, and the nozzle is controlled to move in the converter to spray the uniformly mixed spraying material and water onto the branch component area for spraying and sintering, thereby compensating for the eroded slag layer on the upper part of the component and increasing the thickness of the slag layer coverage.

[0081] When a branch component shows signs of blockage, the same "rinsing" treatment is carried out on the branch component during the production interval. At this time, the function of the special maintenance device is switched to the "rinsing" state, that is, the switching valve is adjusted to connect the blowing pipe to the oxygen interface. Oxygen is injected to "rinse" the excessively thick slag layer in the component area, thinning the covering slag layer, ensuring the air permeability of the bottom blowing component and avoiding blockage.

[0082] Secondly, an embodiment of the present invention provides a high-efficiency control device for converter bottom blowing based on machine vision, comprising:

[0083] The historical furnace data information database establishment module is used to collect historical furnace information and build a historical furnace data information database.

[0084] The converter bottom blowing process simulation module is used to establish a converter model of the blowing process and use Fluent finite element simulation analysis software to simulate the converter bottom blowing process, and obtain the converter bottom blowing flow rate corresponding to the optimal flow field at each time period under various combination conditions.

[0085] The bottom blowing branch real-time detection module is used to detect the data information of each bottom blowing branch online in real time, and input it into the converter model of the blowing process in a timely manner for tracking, analysis and judgment. The data information of each bottom blowing branch includes the flow rate, pressure and deviation from the set value of each bottom blowing branch.

[0086] The visualization detection module is used to visualize and detect the status characteristics of the ventilation elements in each branch of the bottom blowing process during the steel tapping process.

[0087] The adjustment and correction module is used to analyze, calculate, adjust, and correct the real-time monitoring data of each branch of bottom blowing and the visual monitoring data of the permeability elements of each branch of bottom blowing during the tapping process using a converter model of the blowing process, so as to obtain the correction value F of the flow control of each branch of bottom blowing on the time axis under the conditions of this heat. t-i-修正 i is the bottom blowing branch number;

[0088] The model self-learning module is used to adjust the value F. t-i-修正 The data and related information of this furnace are fed back to the historical furnace data information database for model self-learning.

[0089] As one possible implementation of this embodiment, the machine vision-based converter bottom blowing high-efficiency control device further includes:

[0090] The online maintenance module for ventilated elements is used to perform online maintenance on the ventilated elements of each branch of the bottom blowing system using a dedicated maintenance device.

[0091] like Figure 5 As shown, the specific process of using the machine vision-based converter bottom blowing high-efficiency control device of the present invention for machine vision-based converter bottom blowing high-efficiency control is as follows.

[0092] (1) Construct a historical furnace data database: Collect relevant information on historical furnaces, including furnace charging conditions (composition, temperature, and weight of molten iron; type and weight of scrap steel); composition and amount of various slag-forming auxiliary materials; composition, temperature, final slag composition and basicity requirements of the target steel grade; oxygen consumption; endpoint conditions (endpoint composition and temperature); temperature control curves, oxygen lance position control curves, and control curves of each branch of bottom blowing in the converter; refractory lining life, etc.

[0093] (2) Establish a secondary database: Classify, analyze and combine the original data of historical furnaces according to the same or similar principles, and establish a secondary database of various combination types under the same or similar conditions.

[0094] (3) Perform bottom blowing process simulation analysis for each combination type in the secondary database. A converter model of the blowing process was established using SolidWorks software, and the bottom blowing process of the converter was simulated using Fluent finite element simulation analysis software. The velocity vector diagram of the gas-liquid-solid circulation flow in the converter pool under the action of top and bottom combined blowing was analyzed under various combination types. Comparative analysis was conducted to obtain the converter bottom blowing flow rate corresponding to the optimal flow field at each time period under various combination types, including the specific furnace base size, bottom blowing element type and location arrangement, quantity number, and special cases such as poor permeability or blockage of individual branches. The simulation analysis obtained the optimal flow rate value F of each branch of the bottom blowing process corresponding to the optimal flow field at each time period when the molten steel in the pool circulates under the action of bottom blowing gas under various combination types. t-i-模拟 (i is the bottom blowing branch number).

[0095] (4) Online real-time monitoring of flow rate of each branch of bottom blowing: The flow rate, pressure and deviation from the set value of each branch of bottom blowing are monitored online in real time and the data are promptly input into the model for tracking, analysis and judgment.

[0096] (5) Visual detection of the status characteristics of the bottom blowing elements in each branch during the tapping process: During the tapping process, after the converter tilts to the tapping position, the status characteristics of the bottom blowing elements distributed at the bottom of the furnace are photographed and detected by a high-temperature resistant high-definition camera lens. After image recognition, the images are also input into the model and compared with the images of the corresponding numbers of historical furnaces to determine the status trend.

[0097] (6) Model calculation, analysis, adjustment, and correction: The online real-time monitoring data of the flow rate of each branch of bottom blowing and the visualized detection data of the status characteristics of the permeable elements of each branch of bottom blowing during the tapping process are all transmitted to the model for system analysis, calculation, adjustment, and correction to obtain the correction value F of the flow rate control of each branch of bottom blowing on the time axis under the conditions of this heat. t-i-修正 (i is the bottom blowing branch number).

[0098] When the online real-time monitoring of the flow rate of each branch of the bottom blowing system detects an increase in flow rate and a decrease in pressure in a certain branch, it indicates that the erosion of the venting element is intensifying. The model will adjust and reduce the corresponding flow rate of that branch through calculation. Conversely, a decrease in flow rate and an increase in pressure indicate a tendency towards blockage, and the model will appropriately increase the flow rate of that branch through calculation. Similarly, when the visual detection, comparison, and judgment of the status characteristics of the venting elements of each branch of the bottom blowing system during the tapping process show that the venting area of ​​a certain element is increasing and the slag layer covering the venting element is thinning, it indicates that the erosion of that branch is intensifying. The model will correspondingly reduce the flow rate of that branch to prevent the continued aggravation of this state from leading to the scrapping of the element or even a steel leakage accident. Conversely, if it shows that the venting area of ​​a certain branch is gradually decreasing and the slag layer covering the venting element is thickening, it indicates that the branch is showing a tendency towards blockage, and the model will also automatically adjust and increase the flow rate to avoid blockage.

[0099] (7) Online maintenance of bottom-blowing elements: Online maintenance of bottom-blowing elements is carried out through a dedicated maintenance device, which includes a gun body, nozzle, switching valve, cooling system, support frame, spray material, and media such as oxygen, water, and compressed air. It realizes two functions: "spraying" under the condition of intensified erosion and "rinsing" under the condition of blockage. When a branch shows an intensified erosion trend, spraying maintenance is carried out on the branch during the production break. The dedicated maintenance device is switched to the spraying state, and the uniformly mixed spray material and water are sprayed onto the element area of ​​the branch for spraying and sintering to make up for the eroded slag layer on the top of the element and increase the slag layer thickness. When a branch element shows a blockage trend, "rinsing" treatment is also carried out on the branch element during the production break. At this time, the function of the dedicated maintenance device is switched to the "rinsing" state. Oxygen is injected to "rinse" the excessively thick slag layer in the element area, thinning the slag layer, ensuring the air permeability of the bottom-blowing element and avoiding blockage.

[0100] (8) Feedback self-learning: Calculation result correction value F t-i-修正 The data and related information for this furnace run are fed back to the historical database for model self-learning. Specific Implementation Example 1:

[0102] Heater 1: The temperature of the molten iron entering the furnace was 1332℃, and the composition of the molten iron was C: 4.35%; Si: 0.63%; Mn: 0.42%; P: 0.091%; S: 0.023%; the amount of scrap steel and molten iron added was (180+51)t; the amount of main slag-forming materials and alloys added was: lime 28kg / t, dolomite 8.1kg / t, and ore 9.3kg / t; the blowing process was stable, and there was no splashing or re-drying phenomenon. The TSO result of the auxiliary lance at the end of the converter was: [C]: 0.066% and T: 1656℃. The end carbon content and the end temperature were both "double hit" on the first try.

[0103] The converter bottom blowing system is equipped with eight permeable elements, evenly distributed in a staggered pattern on two concentric circles, with four elements on each concentric circle. The simulation analysis yielded the optimal flow field for the bottom blowing branch #2 (taking branch #2 as an example) at different time intervals, corresponding to the optimal flow field obtained under the same or similar combination of conditions as this heat. The simulation control curve F represents the optimal flow rate of the bottom blowing branch #2 (taking branch #2 as an example). t-i-模拟 The corrected control curve F of the bottom blowing branch flow rate on the time axis under this heat condition is obtained by combining "online real-time monitoring of the flow rate of each branch of bottom blowing" and "visual detection of the state characteristics of the permeable elements of each branch of bottom blowing during the tapping process" through model calculation, analysis, adjustment and correction. t-i-修正 like Figure 6 As shown. Specific Implementation Example 2:

[0105] Heater 2: The temperature of the molten iron entering the furnace was 1360℃, and the composition of the molten iron was C: 4.28%; Si: 0.51%; Mn: 0.50%; P: 0.062%; S: 0.030%; the amount of scrap steel and molten iron added was (180+51)t; the amount of main slag-forming materials and alloys added was: lime 29kg / t, dolomite 8.6kg / t, and ore 7.1kg / t; the blowing process was stable, and there was no splashing or re-drying phenomenon. The TSO result of the auxiliary lance at the end of the converter was: [C]: 0.071% and T: 1646℃. The carbon content and the temperature at the end point were both "double hits" on the first try.

[0106] The converter bottom blowing system is equipped with eight permeable elements, evenly distributed in a staggered pattern on two concentric circles, with four elements on each concentric circle. The simulation analysis yielded the optimal flow field for the bottom blowing branch #2 (taking branch #2 as an example) at different time intervals, corresponding to the optimal flow field obtained under the same or similar combination of conditions as this heat. The simulation control curve F represents the optimal flow rate of the bottom blowing branch #2 (taking branch #2 as an example). t-i-模拟 The corrected control curve F of the bottom blowing branch flow rate on the time axis under this heat condition is obtained by combining "online real-time monitoring of the flow rate of each branch of bottom blowing" and "visual detection of the state characteristics of the permeable elements of each branch of bottom blowing during the tapping process" through model calculation, analysis, adjustment and correction. t-i-修正 like Figure 7 As shown.

[0107] This invention classifies, analyzes, and combines historical data under similar or identical conditions, and performs simulation analysis of bottom blowing processes under various combinations. This yields the optimal flow rate F for each branch of the bottom blowing process at different time periods, corresponding to the optimal flow field of the molten steel circulating in the molten pool under the action of bottom blowing gas under various combinations. t-i-模拟 By combining "online real-time monitoring of the flow rate of each branch of bottom blowing" and "visual detection of the status characteristics of the permeable elements of each branch of bottom blowing during the tapping process," model calculations, analysis, adjustments, and corrections were performed to obtain the correction value F for the flow rate control of each branch of bottom blowing on the time axis under the conditions of this heat. t-i-修正 Meanwhile, the timely online maintenance of the bottom blowing elements through a dedicated device greatly improves the lifespan and reblowing effect of the bottom blowing elements, enhances steel quality and production efficiency, reduces process production costs and system maintenance intensity, and achieves efficient control of converter bottom blowing based on machine vision, which has significant economic benefits and broad prospects for promotion.

[0108] An electronic device provided by an embodiment of the present invention includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the device is running, the processor communicates with the memory via the bus, and the processor executes the machine-readable instructions to perform the steps of any of the machine vision-based converter bottom blowing high-efficiency control methods described above.

[0109] Specifically, the aforementioned memory and processor can be general-purpose memory and processor, without any specific limitations. When the processor runs the computer program stored in the memory, it can execute the aforementioned efficient control method for converter bottom blowing based on machine vision.

[0110] Those skilled in the art will understand that the structure of the electronic device does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine some components, or split some components, or have different component arrangements.

[0111] In some embodiments, the electronic device may further include a touchscreen for displaying a graphical user interface (e.g., an application launch screen) and receiving user actions on the graphical user interface (e.g., launching an application). Specifically, the touchscreen may include a display panel and a touch panel. The display panel may be configured as an LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), or similar type. The touch panel can collect user touch or non-touch operations on or near it and generate pre-set operation commands, such as user actions using fingers, styluses, or any suitable object or accessory on or near the touch panel. Additionally, the touch panel may include a touch detection device and a touch controller. The touch detection device detects the user's touch position and posture, and detects the signals generated by the touch operation, transmitting the signals to the touch controller. The touch controller receives touch information from the touch detection device, converts it into information that the processor can process, sends it to the processor, and can also receive and execute commands from the processor. Furthermore, touch panels can be implemented using various types of sensors, including resistive, capacitive, infrared, and surface acoustic wave sensors, as well as any future technologies. Moreover, the touch panel can cover the display panel. Users can operate on or near the touch panel, which is covered by the graphical user interface displayed on the display panel. After detecting the operation on or near the touch panel, the touch panel transmits it to the processor to determine the user input. The processor then responds to the user input by providing corresponding visual output on the display panel. Additionally, the touch panel and display panel can be implemented as two separate components or integrated together.

[0112] Corresponding to the above application startup method, this embodiment of the invention also provides a storage medium storing a computer program, which is executed by a processor to perform the steps of any of the machine vision-based converter bottom blowing high-efficiency control methods described above.

[0113] The application launch device provided in this application embodiment can be specific hardware on the device or software or firmware installed on the device. The device provided in this application embodiment has the same implementation principle and technical effects as the foregoing method embodiments. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the foregoing method embodiments. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can all be referred to the corresponding processes in the above method embodiments, and will not be repeated here.

[0114] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0115] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and there may be other division methods in actual implementation. Furthermore, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interface, and the indirect coupling or communication connection of the apparatus or modules may be electrical, mechanical, or other forms.

[0116] The modules described as separate components may or may not be physically separate. Similarly, the components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0117] In addition, the functional modules in the embodiments provided in this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0118] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0119] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0120] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0121] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

Claims

1. A high-efficiency control method for converter bottom blowing based on machine vision, characterized in that, Includes the following steps: Step S1: Collect historical furnace information and build a historical furnace data information database; Step S2: Establish a converter model for the blowing process and use Fluent finite element simulation analysis software to simulate the converter bottom blowing process, and obtain the converter bottom blowing flow rate corresponding to the optimal flow field for each time period under various combination conditions. Step S3: Real-time online monitoring of the data information of each branch of bottom blowing, and timely input into the converter model of the blowing process for tracking, analysis and judgment. The data information of each branch of bottom blowing includes the flow rate, pressure and deviation from the set value of each branch of bottom blowing. Step S4: Visually detect the status characteristics of the ventilation elements in each branch of the bottom blowing process during the steel tapping process; Step S5: The real-time monitored data of each branch of bottom blowing and the visually monitored state characteristic data of the permeable elements of each branch of bottom blowing during the tapping process are used to perform system analysis, calculation, adjustment and correction using the converter model of the blowing process, to obtain the correction value F of the flow control of each branch of bottom blowing on the time axis under the conditions of this heat. t-i-修正 i is the bottom blowing branch number; Step S6, adjust the value F t-i-修正 The data related to this furnace run is fed back to the historical furnace run data information database for model self-learning; Step S7: Use a dedicated maintenance device to perform online maintenance on the ventilation elements of each branch of the bottom blowing system; The specialized maintenance device includes a nozzle, a gun body, a cooling water pipe, a jetting pipe, a cooling water inlet, a cooling water outlet, a switching valve, an oxygen interface, a spraying interface, and a support frame. The gun body consists of a cooling water pipe and a jetting pipe installed inside the cooling water pipe. The nozzle is located at the front end of the gun body, and the switching valve is located at the rear end. The jetting pipe is connected to the oxygen interface or the spraying interface through the switching valve. The cooling water pipe is equipped with a cooling water inlet and a cooling water outlet. The gun body is mounted on the support frame, and the nozzle extends, retracts, and rotates within the converter. When a branch shows an increasing trend of erosion, the branch is sprayed and maintained during the production break. The special maintenance device is switched to the spraying state, and the evenly mixed spraying material and water are sprayed onto the component area of ​​the branch for spraying and sintering to make up for the eroded slag layer on the upper part of the component and increase the thickness of the slag layer. When a branch component shows signs of blockage, the same "rinsing" treatment is carried out on the branch component during the production interval. At this time, the function of the special maintenance device is switched to the "rinsing" state, and oxygen is injected to "rinse" the excessively thick slag layer in the component area, thereby thinning the covering slag layer.

2. The efficient control method for converter bottom blowing based on machine vision according to claim 1, characterized in that, The historical furnace information includes at least the following: molten iron charging conditions, scrap steel conditions, slag-forming auxiliary materials, target steel grade, oxygen consumption, endpoint conditions, control curves, and furnace lining refractory life. The molten iron charging conditions include the composition, temperature, and weight of the molten iron; the scrap steel conditions include the type and weight of the scrap steel; the slag-forming auxiliary materials include the composition and amount of the slag-forming auxiliary materials added; the target steel grade includes the composition, temperature, final slag composition, and basicity requirements of the target steel grade; the endpoint conditions include the endpoint composition and temperature; and the control curves include the temperature control curve for the blowing process, the oxygen lance position control curve, and the control curves for each branch of the converter bottom blowing process.

3. The efficient control method for converter bottom blowing based on machine vision according to claim 1, characterized in that, Step S2 involves establishing a converter model for the blowing process and using Fluent finite element simulation software to simulate the converter bottom blowing process, obtaining the converter bottom blowing flow rate corresponding to the optimal flow field for each time period under various combination conditions, including: The raw data of historical furnaces are classified, analyzed and combined according to the same or similar principles to establish a secondary database of various combination types under the same or similar conditions; A converter model for the blowing process was established, and for each combination type in the secondary database, the bottom blowing process of the converter was simulated using Fluent finite element simulation analysis software to obtain the converter bottom blowing flow rate corresponding to the optimal flow field at each time period under various combination types.

4. The efficient control method for converter bottom blowing based on machine vision according to claim 3, characterized in that, The process involves establishing a converter model for the blowing process, and using Fluent finite element simulation software to simulate the converter bottom blowing process for each combination type in the secondary database. This yields the converter bottom blowing flow rate corresponding to the optimal flow field at each time period under various combination types, including: A converter model for the blowing process was built using SolidWorks software. The bottom blowing process of the converter was simulated using Fluent finite element simulation analysis software for each combination type in the secondary database. Analyze the velocity vector diagram of the gas-liquid-solid circulation flow in the converter pool under the action of top and bottom blowing under various combination types; Comparative analysis yielded the converter bottom blowing flow rates corresponding to the optimal flow fields at different time periods under various combination conditions. It also yielded the optimal flow rate values ​​F for each branch of the bottom blowing system at different time periods when the molten steel circulates in the molten pool under the action of bottom blowing gas, corresponding to the optimal flow fields. t-i-模拟 i represents the bottom blowing branch number. The various combination conditions include the specific furnace base size, bottom blowing element type and location arrangement, quantity number, and poor permeability or blockage of individual branches.

5. The efficient control method for converter bottom blowing based on machine vision according to claim 1, characterized in that, Step S4 involves visually detecting the state characteristics of the ventilation elements in each branch of the bottom blowing process during steel tapping, including: During the tapping process, after the converter tilts to the tapping position, the state characteristics of the bottom blowing elements distributed at the bottom of the furnace are photographed. After image recognition of the captured images, they are input into the converter model of the blowing process and compared with the corresponding images of historical furnaces to determine the status trend.

6. The efficient control method for converter bottom blowing based on machine vision according to claim 1, characterized in that, In step S5, when the online real-time monitoring of the flow rate of each branch of the bottom blowing process shows that the flow rate of a certain branch increases while the pressure decreases, it indicates that the venting element is showing a trend of intensified erosion. The converter model of the blowing process adjusts and reduces the corresponding flow rate of that branch through calculation. Conversely, if the flow rate decreases while the pressure increases, it indicates a trend of blockage. The converter model of the blowing process appropriately increases the flow rate of that branch through calculation. Similarly, when the visual detection, comparison and judgment of the state characteristics of the permeable elements of each branch of bottom blowing in the steel tapping process are performed, if the area of ​​the permeable area of ​​a certain element increases and the slag layer covered by the permeable element becomes thinner, it indicates that the erosion of that branch is intensified, and the converter model in the blowing process should reduce the flow rate of that branch accordingly. Conversely, if the display shows that the area of ​​the permeable zone in a certain branch is gradually decreasing and the slag layer covered by the permeable element is getting thicker, it indicates that the branch is prone to blockage. The converter model will also automatically adjust and increase the flow rate during the blowing process.

7. A high-efficiency control device for converter bottom blowing based on machine vision, characterized in that, include: The historical furnace data information database establishment module is used to collect historical furnace information and build a historical furnace data information database. The converter bottom blowing process simulation module is used to establish a converter model of the blowing process and use Fluent finite element simulation analysis software to simulate the converter bottom blowing process, and obtain the converter bottom blowing flow rate corresponding to the optimal flow field at each time period under various combination conditions. The bottom blowing branch real-time detection module is used to detect the data information of each bottom blowing branch online in real time, and input it into the converter model of the blowing process in a timely manner for tracking, analysis and judgment. The data information of each bottom blowing branch includes the flow rate, pressure and deviation from the set value of each bottom blowing branch. The visualization detection module is used to visualize and detect the status characteristics of the ventilation elements in each branch of the bottom blowing process during the steel tapping process. The adjustment and correction module is used to analyze, calculate, adjust, and correct the real-time monitoring data of each branch of bottom blowing and the visual monitoring data of the permeability elements of each branch of bottom blowing during the tapping process using a converter model of the blowing process, so as to obtain the correction value F of the flow control of each branch of bottom blowing on the time axis under the conditions of this heat. t-i-修正 i is the bottom blowing branch number; The model self-learning module is used to adjust the value F. t-i-修正 The data related to this furnace run is fed back to the historical furnace run data information database for model self-learning; The ventilation element online maintenance module is used to perform online maintenance on the ventilation elements of each branch of the bottom blowing system using a dedicated maintenance device; The specialized maintenance device includes a nozzle, a gun body, a cooling water pipe, a jetting pipe, a cooling water inlet, a cooling water outlet, a switching valve, an oxygen interface, a spraying interface, and a support frame. The gun body consists of a cooling water pipe and a jetting pipe installed inside the cooling water pipe. The nozzle is located at the front end of the gun body, and the switching valve is located at the rear end. The jetting pipe is connected to the oxygen interface or the spraying interface through the switching valve. The cooling water pipe is equipped with a cooling water inlet and a cooling water outlet. The gun body is mounted on the support frame, and the nozzle extends, retracts, and rotates within the converter. When a branch shows an increasing trend of erosion, the branch is sprayed and maintained during the production break. The special maintenance device is switched to the spraying state, and the evenly mixed spraying material and water are sprayed onto the component area of ​​the branch for spraying and sintering to make up for the eroded slag layer on the upper part of the component and increase the thickness of the slag layer. When a branch component shows signs of blockage, the same "rinsing" treatment is carried out on the branch component during the production interval. At this time, the function of the special maintenance device is switched to the "rinsing" state, and oxygen is injected to "rinse" the excessively thick slag layer in the component area, thereby thinning the covering slag layer.

8. An electronic device, characterized in that, The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions that the processor can execute. When the electronic device is running, the processor communicates with the memory via the bus, and the processor executes the machine-readable instructions to perform the steps of the machine vision-based converter bottom blowing high-efficiency control method as described in any one of claims 1-6.

9. A storage medium, characterized in that, The storage medium stores a computer program that, when executed by a processor, performs the steps of the machine vision-based efficient control method for converter bottom blowing as described in any one of claims 1-6.

Images