Converter smelting temperature monitoring method based on machine vision
By using machine vision technology during converter steelmaking, combining flame information analysis and infrared temperature measurement, and real-time adjustment of temperature, the problem of insufficient temperature control accuracy in the existing technology is solved, efficient and accurate temperature control is achieved, and steel is improved Quality and productivity.
Patent Information
- Application Number
- CN202411256404.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-09
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2044-09-09
AI Technical Summary
The existing converter steelmaking temperature control methods lack real-time correction and dynamic adjustment, resulting in limited control accuracy and easy deviation, affecting the stability of the steelmaking process and steel grade quality.
Using a machine vision-based method, the temperature-time control curve is detected through the furnace port flame information analysis system and the online infrared temperature measurement device, and a model is established based on historical data, and the temperature is adjusted in real time, and the furnace port and steel outlet temperatures are dynamically corrected. , realize accurate control of process and end point temperature.
It improves the control accuracy of the end point temperature of the converter smelting, reduces the occurrence of abnormal phenomena such as splashing and back-drying, ensures the smooth and efficient operation of the blowing process, and improves the quality and production efficiency of the steel seeds.
Smart Images

Figure CN119040547A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the field of converter steelmaking process control, and in particular relates to a converter smelting temperature monitoring method based on machine vision. Background Art
[0002] BOF steelmaking is one of the key links in steel production and has been widely used and promoted. Stable control of the end point of BOF smelting is an important guarantee for the quality and safety of BOF production. The specific objectives of end point control are: (1) The carbon content of molten steel should reach the target range required for the steel grade being produced; (2) The phosphorus and sulfur content of molten steel should be lower than the range required by the lower limit of the specification; (3) The tapping temperature should ensure the smooth progress of the next step; (4) The molten steel has appropriate oxidizability. End point control is essentially the control of the BOF blowing process. The quality of end point control directly affects the productivity, metal recovery rate, production cost and steel quality of steelmaking, and is a very important link in the operation of BOF steelmaking process.
[0003] Molten steel temperature is an important parameter in converter smelting. Appropriate temperature is the primary condition for all steelmaking reactions in the molten pool. Factors affecting molten steel temperature in production include molten iron composition, molten iron temperature, molten iron ratio, furnace age, charging and slag making, blowing gun position, etc. Molten steel temperature control mainly involves process temperature control and endpoint temperature control, and precise control of endpoint temperature directly affects technical indicators such as energy in the smelting process, alloy element recovery rate, furnace lining service life, and quality of finished steel. However, converter steelmaking is a complex physical and chemical process at high temperature, and it is impossible to monitor the temperature in the molten pool online in real time by direct temperature measurement. Existing converter steelmaking temperature control methods mostly rely on static models of reaction mechanism, material balance and thermodynamics or rely on manual experience assessment. For example, CN117272788A discloses a method for predicting the temperature of the molten pool. Based on the change of the inlet and outlet water temperature of the converter oxygen lance, the converter temperature at the end of the static model is predicted through the heat transfer principle and related calculations, combined with the BP neural network algorithm. The prediction of the molten pool temperature mainly involves the measurement results of the auxiliary lance, the control height of the oxygen lance, the cooling water conditions of the oxygen lance, etc. CN111893237A discloses a method for real-time prediction of the carbon content and temperature of the molten pool in converter steelmaking. The invention only performs functional data analysis based on the raw material data, smelting process data, molten pool carbon content and temperature information data of several historical furnaces to predict the carbon content and temperature of the molten pool, without considering the changes in real-time data and conditions for dynamic correction. CN117553921A discloses a method, system, terminal and storage medium for predicting the temperature of molten steel in a converter. The method uses converter smelting data and auxiliary gun measurement data, in conjunction with flame temperature collection at the furnace mouth, to perform neural network calculations to predict the temperature of molten steel.
[0004] The above prediction methods lack real-time correction and dynamic adjustment of the model, have limited control accuracy, and are prone to deviations, which lead to frequent abnormal conditions in the steelmaking process. The resulting deviations will also directly affect the control of the converter endpoint temperature and carbon content, and thus affect the overall rhythm of steelmaking, the recovery rate of energy and alloy elements, the quality of steel grades, and the stability control of production line safety, which is not conducive to the intelligent and high-quality development of the steel and metallurgical industry. Summary of the invention
[0005] In view of the above problems, the present invention provides a converter smelting temperature monitoring method based on machine vision, by respectively arranging a furnace mouth flame information analysis system and an online infrared temperature measuring device at the furnace mouth and the tapping port to obtain a temperature-time control curve, and then combining historical furnace data to establish a furnace mouth and tapping port detection temperature-time control curve model under various conditions; according to the same or similar classification principles, the model recommended curve is applied, the real-time temperature is compared with the curve temperature recommended by the model at that moment, and the furnace mouth and tapping port temperatures are timely corrected and dynamically adjusted to maintain the consistency of the actual temperature and the recommended temperature, thereby achieving effective control of the process and terminal temperature, reducing the occurrence of abnormal phenomena such as splashing, back drying, and unreasonable temperature rise, ensuring the smooth, efficient and reasonable operation of the blowing process, and greatly improving the control accuracy of the converter smelting terminal temperature.
[0006] In order to achieve the above effects, the present invention adopts the following technical solutions:
[0007] A converter smelting temperature monitoring method based on machine vision collects historical furnace data including furnace mouth and tapping port temperature-time control curves detected by a flame information analysis system and an online infrared temperature measuring device, classifies and combines them according to the same or similar principles, and fits the optimal control model of the furnace mouth and tapping port temperature; then compares the real-time detected temperature with the recommended temperature of the model curve, performs dynamic correction and adjustment of the real-time temperature, and controls the process and terminal temperature.
[0008] The above scheme includes the following specific steps:
[0009] (1) Furnace mouth temperature detection, obtain the furnace mouth temperature-time control curve T 炉口(t) ;
[0010] (2) Detect the tapping temperature and obtain the tapping temperature-time control curve T 出钢口(t) ;
[0011] (3) Collection includes T 炉口(t) and T 出钢口(t) The historical furnace information of converter smelting is collected and a historical database is established;
[0012] (4) Preprocess the historical data, classify and combine them according to the same or similar principles, and establish a secondary database;
[0013] (5) T in the secondary database 炉口(t) and T 出钢口(t) Perform data fitting to obtain the optimal control model T under different classification conditions 炉口(t)-推荐 and T 出钢口(t)-推荐 ;
[0014] (6) Apply the optimal curve recommended by the model according to the same or similar principles, compare the real-time furnace mouth and tapping port temperatures with the temperatures recommended by the model at that moment, adjust the actual temperatures in a timely manner, maintain the consistency between the actual temperatures and the recommended temperatures, and control the process and end temperatures;
[0015] (7) After the furnace is completed, the actual control curve T is obtained 炉口(t)-实际 and T 出钢口(t)-实际 , all data and calculation results are fed back to the model for self-learning.
[0016] Furthermore, the furnace mouth temperature detection method in step (1) is to set up a furnace mouth flame information analysis system to accurately analyze and judge the image characteristics and spectral characteristics of the converter furnace mouth flame, form a series of furnace mouth temperatures corresponding to any moment on the time axis of the blowing process, and obtain the furnace mouth detection temperature-time control curve T of the entire blowing process of the furnace 炉口(t) .
[0017] Furthermore, the tapping port temperature detection method in step (2) is to install an online infrared temperature measuring device in the tapping port to detect the temperature and change trend in the converter molten pool, form a series of tapping port temperatures corresponding to any moment on the time axis of the blowing process, and obtain the tapping port detection temperature-time control curve T of the entire blowing process of the furnace. 出钢口(t) .
[0018] Furthermore, the historical furnace information in step (3) includes the temperature and amount of molten iron entering the furnace, the content of C, Si, Mn, P, S in the molten iron, the amount of scrap steel added, the amount of lime, dolomite and iron ore added, the end temperature and the end carbon content. The conditions for molten iron entering the furnace, the composition and amount of slag-making auxiliary materials determine the total heat, initial temperature, process temperature, heating rate, and end temperature of the process through the steelmaking material balance and heat balance, and are closely related to the temperature of the furnace mouth and the steel outlet at any time during the process.
[0019] Furthermore, the preprocessing in step (4) is to eliminate invalid, useless, and highly biased data.
[0020] Furthermore, the same or similar principle in step (4) is to set the data classification interval range, and the pre-processed historical furnace data is reclassified. The classification interval is: the C content in the molten iron is a classification interval of 0.01%, and the interval value is: 0.351% to 0.361%, 0.361% to 0.371%, 0.371% to 0.381%, and so on; the Si and Mn content in the molten iron is a classification interval of 0.1%, and the interval value is: 0 to 0.1%, 0.1% to 0.2%, 0.2% to 0.3%, and so on; the P content in the molten iron is a classification interval of 0.01%, and the interval value is: The values are: 0.071%~0.081%, 0.081%~0.091%, 0.091%~0.11%, and so on; the S content in molten iron is classified into 0.01% intervals, and the interval values are: 0.011%~0.021%, 0.021%~0.031%, 0.031%~0.041%, and so on; the amount of scrap steel added is classified into 5000kg intervals; the amount of lime, dolomite and iron ore added is classified into 500kg intervals; the blowing end temperature is classified into 5°C intervals; the endpoint values of the above classification intervals are all aggregated into the previous classification interval.
[0021] Furthermore, the data fitting formula in step (5) is: T0=polyval(a,t), a=polyfit(tdata,Tdata,n);
[0022] Among them, n is the highest order of the polynomial, tdata is the time array, and Tdata is the temperature array, all of which are input in array form.
[0023] Furthermore, the temperature adjustment method of the process in step (6) is to adjust the height of the blowing oxygen lance or add iron ore. When the temperature rises quickly, the oxygen lance height is appropriately increased to slow down the carbon-oxygen reaction rate and reduce the heating temperature. Iron ore can also be added for cooling to inhibit the heating rate. When the temperature rises slowly, the oxygen lance height is appropriately lowered to promote the carbon-oxygen reaction rate and increase the heating rate.
[0024] A computer program for implementing the above-mentioned converter smelting temperature monitoring method based on machine vision.
[0025] An information processing terminal for implementing the above-mentioned converter smelting temperature monitoring method based on machine vision.
[0026] A computer-readable storage medium includes instructions, which, when executed on a computer, enable the computer to execute the above-mentioned converter smelting temperature monitoring method based on machine vision.
[0027] Beneficial effects:
[0028] (1) The present invention can realize accurate monitoring of real-time temperature by applying high-precision temperature detection devices such as a furnace mouth flame information analysis system and an online infrared temperature measuring device; secondly, combined with the optimal control curve recommended by the model, real-time comparison, prediction, and judgment are performed, and the gun height and feeding are adjusted and corrected in time, so as to ensure that the operation process is carried out according to the preset optimal heating trend, realize accurate control of process temperature, reduce the occurrence of abnormal phenomena such as splashing, back drying, and unreasonable heating, effectively ensure the smooth, safe, efficient, and reasonable operation of the blowing process, and improve the hit rate of the converter terminal target temperature.
[0029] (2) The application of the model of the present invention can achieve high-precision control of the endpoint temperature. The model can be applied to the production of different steel grades, promote the production of high-quality steel grades, effectively improve production efficiency and reduce production costs. It has significant economic benefits and broad promotion prospects, and is conducive to the intelligent and high-quality development of the steel and metallurgical industry. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] Figure 1 The network structure diagram of the converter smelting temperature monitoring method based on machine vision;
[0031] Figure 2 The furnace temperature-time control curve T of Example 1 is 炉口(t) , T 炉口(t)-推荐 and T 炉口(t)-实际 Trend chart of
[0032] Figure 3 The tapping port temperature-time control curve T of Example 1 is 出钢口(t) , T 出钢口(t)-推荐 and T 出钢口(t)-实际 Trend chart of
[0033] Figure 4 The furnace temperature-time control curve T of Example 2 is 炉口(t) , T 炉口(t)-推荐 and T 炉口(t)-实际 Trend chart of
[0034] Figure 5 The tapping port temperature-time control curve T of Example 2 is 出钢口(t) , T 出钢口(t)-推荐 and T 出钢口(t)-实际 trend chart. DETAILED DESCRIPTION
[0035] The following will combine the contents in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0036] (1) Furnace mouth temperature detection: A furnace mouth flame information analysis system is set at the furnace mouth to analyze and accurately judge the image characteristics and spectral characteristics of the converter furnace mouth flame, obtain a series of furnace mouth temperatures corresponding to any moment on the time axis of the blowing process, and obtain the furnace mouth detection temperature-time curve T for the whole blowing process control. 炉口 (t);
[0037] (2) Temperature detection at the tapping port: An online infrared temperature measuring device is installed at the tapping port to timely detect the temperature and change trend in the converter molten pool, forming a series of tapping port temperatures corresponding to any moment on the time axis of the blowing process, and obtaining the tapping port detection temperature-time curve T for the entire blowing process control of the furnace. 出钢口 (t);
[0038] (3) The temperature and amount of molten iron in the furnace, the content of C, Si, Mn, P, S in the molten iron, the amount of scrap steel added, the amount of lime, dolomite and iron ore added, the end point temperature, the end point carbon content and the detection temperature-time curve T of each furnace 炉口(t) and T 出钢口(t) Carry out data collection and establish historical database;
[0039] (4) Invalid, useless, and large-deviation historical data are eliminated, and classified and combined according to the same or similar principles to establish a secondary database. The classification intervals are: C content in molten iron is classified into a classification interval of 0.01% each, and the interval values are: 0.351% to 0.361%, 0.361% to 0.371%, 0.371% to 0.381%, and so on; Si and Mn content in molten iron is classified into a classification interval of 0.1% each, and the interval values are: 0 to 0.1%, 0.1% to 0.2%, 0.2% to 0.3%, and so on; P content in the molten iron is classified into a classification interval of 0.01% each, and the interval values are: 0.071%~0.081%, 0.081%~0.091%, 0.091%~0.11%, and so on; the S content of molten iron is classified into a range of 0.01% each, and the range values are: 0.011%~0.021%, 0.021%~0.031%, 0.031%~0.041%, and so on; the amount of scrap steel added is classified into a range of 5000kg each; the amount of lime, dolomite and iron ore added is classified into a range of 500kg each; the blowing end temperature is classified into a range of 5℃ each; the endpoint values of the above classification ranges are all aggregated into the previous classification range;
[0040] (5) T in the secondary database 炉口(t) and T 出钢口(t) Perform data fitting to obtain the best control model T 炉口(t)-推荐 and T 出钢口(t)-推荐 , and load the model into a computer;
[0041] The furnace mouth temperature fitting formula is: T 0-炉口 =polyval(a,t -炉口 ), a = polyfit(t -炉口 data,T -炉口 data,n);
[0042] n is the highest order of the polynomial, t -炉口 data is the furnace mouth time array, T -炉口 Data is the furnace mouth temperature array, all input in array form;
[0043] The fitting formula of the tapping temperature is: T 0-出钢口 =polyval(a,t -出钢口 ), a = polyfit(t -出钢口 data,T -出钢口 data,n);
[0044] n is the highest order of the polynomial, t -出钢口 data is the tapping time array, T -出钢口data is the tapping temperature array, all of which are input in array form.
[0045] (6) Based on the same or similar principles, apply the best curve T recommended by the model 炉口(t)-推荐 and T 出钢口(t)-推荐 , the real-time temperature detected by the furnace mouth flame information analysis system and the tapping port online infrared temperature measuring device is compared with the temperature value recommended by the model curve at that moment, and the real-time temperature is adjusted in time (when the temperature rises quickly, the oxygen lance height is appropriately increased to slow down the carbon-oxygen reaction rate and reduce the heating temperature. Iron ore can also be added for cooling to inhibit the heating rate. When the temperature rises slowly, the oxygen lance height is appropriately lowered to promote the carbon-oxygen reaction rate and increase the heating rate), the actual temperature is kept consistent with the recommended temperature, and the process and terminal temperature are precisely controlled;
[0046] (7) After the furnace is completed, the actual control curve T will be obtained 炉口(t)-实际 and T 出钢口(t)-实际 , all data and calculation results are fed back to the model for self-learning.
[0047] A computer program for implementing the above-mentioned converter smelting temperature monitoring method based on machine vision.
[0048] An information processing terminal for implementing the above-mentioned converter smelting temperature monitoring method based on machine vision.
[0049] A computer-readable storage medium includes instructions, which, when executed on a computer, enable the computer to execute the above-mentioned converter smelting temperature monitoring method based on machine vision.
[0050] The network structure diagram of the converter smelting temperature monitoring model control method based on machine vision of the present invention is as follows Figure 1 shown.
[0051] Example 1
[0052] The model obtained by the present invention is applied to the converter smelting of this batch. The converter smelting end point target values are: the end point temperature is 1636°C, and the end point carbon is 0.081%. The specific operation steps are as follows:
[0053] (1) Converter smelting: The temperature of the molten iron in the furnace is 1386℃. The amount of scrap steel and molten iron added are 180t and 51t respectively. The composition of the molten iron is C: 4.40%, Si: 0.65%, Mn: 0.35%, P: 0.082%, S: 0.028%; the amount of main slag materials and alloy added: lime 30kg / t, dolomite 9kg / t, ore 10kg / t; oxygen consumption 49m 3 / t;
[0054] (2) Input the furnace entry conditions and smelting conditions in step (1) into the computer, and select the optimal control curve T recommended by the model for this batch. 炉口(t)-推荐 and T 出钢口(t)-推荐 ,like Figure 2 , 3 As shown;
[0055] (3) The real-time temperature obtained by the furnace mouth flame information analysis system and the tapping port online infrared temperature measuring device of this furnace is compared with the curve temperature recommended by the model at that moment, and the process temperature is dynamically corrected and adjusted in time. When the temperature rises quickly, the oxygen lance height is appropriately increased to slow down the carbon-oxygen reaction rate and reduce the heating temperature. Iron ore can also be added for cooling to inhibit the heating rate; when the temperature rises slowly, the oxygen lance height is appropriately lowered to promote the carbon-oxygen reaction rate and increase the heating rate; the actual temperature and the recommended temperature are kept consistent to achieve precise control of the end temperature, and the end temperature is 1635°C and the end carbon content is 0.080%;
[0056] (4) After the current heat is completed, the actual control curve T 炉口(t)-实际 and T 出钢口(t)-实际 All data and calculation results are fed back to the model for self-learning. The curve results are as follows Figure 2 , 3 shown.
[0057] The converter smelting and blowing process of this batch was stable, without splashing and drying, the end point temperature was 1635°C, the end point carbon content was 0.080%, the end point was hit once, the end point temperature error was 1°C, the end point carbon error was 0.001%, and the end point temperature and end point carbon content were all qualified. The converter end point temperature monitoring model based on machine vision of the present invention can realize the real-time correction of the process temperature and achieve high-precision control of the end point temperature.
[0058] Example 2
[0059] The model obtained by the present invention is applied to the converter smelting of this batch, and the converter smelting end point target values are: the end point temperature is 1645°C, and the end point carbon is 0.076%. The specific steps are as follows:
[0060] (1) Converter smelting: The temperature of the molten iron in the furnace is 1372℃. The amount of scrap steel and molten iron added are 180t and 51t respectively. The composition of the molten iron is C: 4.28%, Si: 0.58%, Mn: 0.42%, P: 0.072%, S: 0.032%; the amount of main slag materials and alloy added: lime 30kg / t, dolomite 8.2kg / t, iron ore 9.6kg / t; oxygen consumption 49.2m 3 / t;
[0061] (2) Input the furnace entry conditions and smelting conditions in step (1) into the computer, and select the optimal control curve T recommended by the model for this batch. 炉口(t)-推荐 and T 出钢口(t)-推荐 ,like Figure 4 , 5 As shown;
[0062] (3) The real-time temperature obtained by the furnace mouth flame information analysis system and the online infrared temperature measuring device at the steel outlet is compared with the curve temperature value recommended by the model at that moment, and the process temperature is dynamically corrected and adjusted in time. When the temperature rises quickly, the oxygen lance height is appropriately increased to slow down the carbon-oxygen reaction rate and reduce the heating temperature. Iron ore can also be added for cooling to inhibit the heating rate. When the temperature rises slowly, the oxygen lance height is appropriately lowered to promote the carbon-oxygen reaction rate and increase the heating rate. The actual temperature and the recommended temperature are kept consistent to achieve precise control of the terminal temperature. The terminal temperature is 1646°C and the terminal carbon content is 0.077%.
[0063] (4) After the current heat is completed, the actual control curve T 炉口(t)-实际 and T 出钢口(t)-实际 All data and calculation results are fed back to the model for self-learning. The curve results are as follows Figure 4 , 5 shown.
[0064] The converter smelting and blowing process of this batch is stable, without splashing and drying, the end point temperature is 1646℃, the end point carbon content is 0.077%, the end point is hit once, the end point temperature error is 1℃, the end point carbon error is 0.001%, and the end point temperature and end point carbon content are all qualified. The converter end point temperature monitoring model based on machine vision of the present invention effectively ensures the stable, efficient and reasonable operation of the blowing process, and improves the hit rate of the converter end point target temperature.
[0065] In summary, Figure 2-5 It can be seen that the model recommends curve T 炉口(t)-推荐 and T 出钢口(t)-推荐 The T obtained by the furnace flame information analysis system and the tapping port online infrared temperature measurement device 炉口 (t) and T 出钢口 (t) and the actual control curve T 炉口(t)-实际 and T 出钢口(t)-实际 The high degree of fit fully confirms the rationality and effectiveness of the converter smelting temperature monitoring method based on machine vision obtained by the present invention.
Claims
1. A method for monitoring converter smelting temperature based on machine vision, characterized in that: Collect historical furnace data including furnace mouth and tapping port temperature-time control curves detected by flame information analysis system and online infrared temperature measuring device, classify and combine them according to the same or similar principles, and fit the optimal control model of furnace mouth and tapping port temperature; then compare the real-time detected temperature with the recommended temperature of the model curve, dynamically correct and adjust the real-time temperature, and control the process and terminal temperature.
2. The converter smelting temperature monitoring method according to claim 1 is characterized in that: The method comprises the following specific steps: (1) Furnace mouth temperature detection, obtain the furnace mouth temperature-time control curve T 炉口(t) ; (2) Detect the tapping temperature and obtain the tapping temperature-time control curve T 出钢口(t) ; (3) Collection includes T 炉口(t) and T 出钢口(t) The historical furnace information of converter smelting is collected and a historical database is established; (4) Preprocess the historical data, classify and combine them according to the same or similar principles, and establish a secondary database; (5) T in the secondary database 炉口(t) and T 出钢口(t) Perform data fitting to obtain the optimal control model T under different classification conditions 炉口(t)-推荐 and T 出钢口(t)-推荐 ; (6) Apply the optimal curve recommended by the model according to the same or similar principles, compare the real-time furnace mouth and tapping port temperatures with the temperatures recommended by the model at that moment, adjust the actual temperatures in a timely manner, maintain the consistency between the actual temperatures and the recommended temperatures, and control the process and end temperatures; (7) After the furnace is completed, the actual control curve T is obtained 炉口(t)-实际 and T 出钢口(t)-实际 , all data and calculation results are fed back to the model for self-learning.
3. The converter smelting temperature monitoring method according to claim 2 is characterized in that: The furnace mouth temperature detection method in step (1) is to set up a furnace mouth flame information analysis system to accurately analyze and judge the image characteristics and spectral characteristics of the converter furnace mouth flame, form a series of furnace mouth temperatures corresponding to any moment on the time axis of the blowing process, and obtain the furnace mouth detection temperature-time control curve T of the entire blowing process of the furnace. 炉口(t) .
4. The converter smelting temperature monitoring method according to claim 2 is characterized in that: The tapping port temperature detection method in step (2) is to install an online infrared temperature measuring device in the tapping port to detect the temperature and change trend in the converter molten pool, form a series of tapping port temperatures corresponding to any moment on the time axis of the blowing process, and obtain the tapping port detection temperature-time control curve T of the entire blowing process of the furnace. 出钢口(t) .
5. The converter smelting temperature monitoring method according to claim 2 is characterized in that: The historical furnace information in step (3) includes the temperature and amount of molten iron entering the furnace, the contents of C, Si, Mn, P, and S in the molten iron, the amount of scrap steel added, the amount of lime, dolomite, and iron ore added, the end point temperature, and the end point carbon content.
6. The converter smelting temperature monitoring method according to claim 2 is characterized in that: The pretreatment in step (4) is to eliminate invalid, useless, and large-deviation data; the same or similar principle is to set the data classification interval range, and to reclassify the pretreated historical furnace data, and the classification interval is: the C content in the molten iron is a classification interval of 0.01%, and the interval value is: 0.351% to 0.361%, 0.361% to 0.371%, 0.371% to 0.381%, and so on; the Si and Mn contents in the molten iron are a classification interval of 0.1%, and the interval value is: 0 to 0.1%, 0.1% to 0.2%, 0.2% to 0.3%, and so on; the P content in the molten iron is a classification interval of 0.01%. The S content in molten iron is classified into 0.01% to 0.021%, 0.021% to 0.031%, 0.031% to 0.041%, and so on; the amount of scrap steel added is classified into 5000kg as one classification interval; the amount of lime, dolomite and iron ore added is classified into 500kg as one classification interval; the blowing endpoint temperature is classified into 5°C as one classification interval; the endpoint values of the above classification intervals are all aggregated into the previous classification interval.
7. The converter smelting temperature monitoring method according to claim 2 is characterized in that: The data fitting formula in step (5) is: T0=polyval(a,t), a=polyfit(tdata,Tdata,n); Among them, n is the highest order of the polynomial, tdata is the time array, and Tdata is the temperature array, all of which are input in array form.
8. A computer program for implementing the method for monitoring converter smelting temperature based on machine vision as described in any one of claims 1 to 7.
9. An information processing terminal for implementing the method for monitoring converter smelting temperature based on machine vision as described in any one of claims 1 to 7.
10. A computer-readable storage medium, comprising instructions, which, when executed on a computer, enable the computer to execute the method for monitoring converter smelting temperature based on machine vision as described in any one of claims 1 to 7.
Citation Information
Patent Citations
Real-time determining method and system for carbon content and temperature value of molten steel in steelmaking later stage
CN109975507A
Prediction system and method for judging converter steelmaking endpoint temperature on basis of flame images
CN113718082A
Molten steel quality multi-task prediction method based on fractal evolution learning
CN116993172A
Converter molten steel temperature prediction method and system, terminal and storage medium
CN117553921A
Converter automatic slag splashing gun position control method and device, electronic equipment and storage medium
CN118028565A
Cited By
Converter smelting state monitoring method, device and equipment based on multi-modal large model
CN121185372A
