Accurate control method and system for heating temperature rise of ladle refining furnace

Abstract

The invention provides a method and a system for accurately controlling the heating temperature rise of a ladle refining furnace. The method comprises the following steps of: constructing a historical heat data information base; pre-processing the heating temperature rise value of the historical heat of each condition, and optimizing a first temperature rise heating parameter of the heat; a theoretical second heating temperature rise parameter is obtained through electric power heat balance calculation; the steel ladle infrared thermal imaging detection data of the historical heat and the corresponding molten steel temperature in the steel ladle are subjected to correlation analysis, and a third heating temperature rise parameter of the heat is obtained; inputting the first heating temperature rise parameter, the second heating temperature rise parameter and the third heating temperature rise parameter into a convolutional neural network, and outputting a recommended fourth heating temperature rise parameter; and a fifth heating temperature rising parameter of the current heat is obtained, the fourth heating temperature rising parameter and the fifth heating temperature rising parameter are compared to obtain an actual heating parameter of the current heat, and accurate control over the temperature of the current heat is achieved according to the actual heating parameter. Based on the method, the invention further provides a system for accurately controlling the heating temperature rise of the ladle refining furnace. According to the invention, accurate control of the temperature of the furnace is realized.

Description

Technical Field

[0001] The invention belongs to the technical field of steelmaking temperature control, and in particular relates to a heating and temperature-raising precise control method and system for a ladle refining furnace. Background Art

[0002] Ladle is an important container for transporting molten steel and conducting secondary metallurgical reactions in converter and continuous casting processes. Its management and scheduling play an important role in optimizing production operations and energy saving and consumption reduction. LF ladle refining furnace is the main off-furnace refining equipment in steel production, which is actually a special form of electric arc furnace. LF refining furnace is heated by three electrodes. When heating, the electrodes are inserted into the slag layer and the submerged arc heating method is adopted. This method has small radiation, protective effect on the furnace lining, high heating efficiency and good thermal efficiency. At the same time, the equipment is simple, the investment cost is low, the operation is flexible and the refining effect is good, which has been widely used and developed. LF furnace refining is one of the main methods of off-furnace refining. Its function is to quickly make white slag. White slag has strong reducibility in LF furnace. This is the result of the interaction of good reducing atmosphere and argon stirring in LF furnace. The purpose of LF slag making is desulfurization, deoxidation, improving alloy yield and removing inclusions. The rapid and stable production of reducible white slag with good fluidity and certain emulsification in LF is necessary for LF desulfurization, adsorption of inclusions and ensuring the quality of molten steel.

[0003] LF furnace temperature raising is to use electric arc heating in a non-oxidizing atmosphere to increase the temperature of molten steel, compensate for the temperature drop of molten steel during the treatment process and the endothermic heat of slag making and alloying, and facilitate the formation of ladle slag that is conducive to desulfurization, deoxidation, and removal of inclusions. The desulfurization reaction is an endothermic reaction. Increasing the temperature is conducive to the refining desulfurization reaction. The slag is heated by electrodes to produce a higher temperature, which provides better thermodynamic conditions for the desulfurization reaction. However, excessively increasing the temperature of molten steel slag is not conducive to improving the service life of the ladle lining and controlling the power consumption cost. Therefore, accurate and efficient heating and temperature raising to provide the next process with a suitable molten steel temperature is one of the main functions of the LF refining furnace and an important guarantee for safe and smooth production. Refining temperature rise should comprehensively consider the life and condition of the ladle, the air permeability of the ladle bottom blowing, the turnover of the ladle, the steel tapping temperature of the converter and the charging of the ladle, the auxiliary and waiting time, the refining charging and wire feeding, the argon blowing and weak stirring time, the target temperature at the end of the treatment, etc. The electrode heating temperature rise value should be accurately determined according to various temperature influencing factors, and then the heating time should be determined in combination with the voltage and current of the electrode heating.

[0004] In view of the wide range of temperature influencing factors mentioned above and the many unstable factors, the heating of the refining electrode is greatly passive. If the heating time is not enough, the temperature cannot reach the target temperature and secondary heating is required, which will have a great impact on the ladle refractory, electrode life, molten steel quality and production rhythm; on the contrary, if the heating time is too long, it will not only waste electricity but also increase the production cost per ton of steel. Summary of the invention

[0005] In order to solve the above technical problems, the present invention proposes a method and system for accurately controlling the heating and temperature rise of a ladle refining furnace, which realizes accurate control of the temperature of the furnace, significantly improves production efficiency and reduces production costs.

[0006] To achieve the above object, the present invention adopts the following technical solutions:

[0007] A method for accurately controlling the heating temperature rise of a ladle refining furnace comprises the following steps:

[0008] Obtain the ladle data of historical furnaces and the relevant factors affecting the temperature of molten steel, and build a historical furnace data information database; pre-process the heating and temperature rise values ​​of historical furnaces under various conditions to deduce the first heating and temperature rise parameters of the furnace; perform power heat balance calculation based on the initial temperature of molten steel, target temperature of molten steel, heating temperature and heat loss during the heating process of historical furnaces to obtain the theoretical second heating and temperature rise parameters; perform correlation analysis on the infrared thermal imaging detection data of the ladle of historical furnaces and the corresponding molten steel temperature in the ladle to obtain the third heating and temperature rise parameters of the furnace;

[0009] Inputting the first heating parameter, the second heating parameter and the third heating parameter into the input layer of the convolutional neural network, using the convolutional neural network to predict, and outputting the recommended fourth heating parameter through the output layer;

[0010] Obtain the fifth heating temperature rise parameter of the current furnace, compare the fourth heating temperature rise parameter with the fifth heating temperature rise parameter to obtain the actual heating parameter of the current furnace, and realize accurate control of the temperature of the current furnace according to the actual heating parameter of the current furnace.

[0011] Furthermore, after comparing the fourth heating temperature rise parameter with the fifth heating temperature rise parameter to obtain the actual heating parameter of the current furnace, it also includes obtaining the actual temperature of the current furnace according to the actual heating parameter of the current furnace.

[0012] Furthermore, the process of achieving accurate control of the current furnace temperature according to the comparison result includes:

[0013] When the actual heating parameter is greater than the fourth heating temperature rise parameter, the heating speed is reduced by reducing the heating power;

[0014] When the actual heating parameter is less than the fourth heating temperature rise parameter, the heating speed is increased by increasing the heating power.

[0015] Furthermore, the relevant factors affecting the molten steel temperature include ladle life, ladle state, ladle bottom blowing permeability, ladle turnover, converter tapping temperature, ladle charging, LF process assistance and waiting time after tapping, refining charging and wire feeding, argon blowing and weak stirring time, refining electrode heating parameters of the corresponding furnace and the target temperature for the end of treatment.

[0016] Furthermore, the first temperature rise heating parameter includes a heating time optimal value, and a current optimal value and a voltage optimal value corresponding to the heating time optimal value;

[0017] The first temperature rise heating parameter includes a heating time theoretical value, and a current theoretical value and a voltage theoretical value corresponding to the heating time theoretical value;

[0018] The third temperature rise heating parameter includes a heating time detection value, and a current detection value and a voltage detection value corresponding to the time detection value.

[0019] Furthermore, the process of pre-processing the heating temperature rise values ​​of the historical furnaces under each condition to deduce the first heating parameter of the furnace includes: performing abnormal cleaning on the heating temperature rise values ​​of the historical furnaces under each condition, eliminating the abnormal data and then performing linear regression analysis to obtain the corresponding data with the highest probability under various conditions, that is, the first heating parameter.

[0020] Furthermore, the process of performing electric heat balance calculation to obtain the theoretical second heating temperature rise parameter according to the initial temperature of the molten steel, the target temperature of the molten steel, the heating temperature and the heat loss during the heating process of the historical furnaces includes:

[0021] T 初始温度 -T 热损失 +T 加热温度 =T 目标温度 ;

[0022] Theoretical value of heating time = theoretical heat / (power × efficiency);

[0023] Wherein, heat refers to the theoretical heat capacity of the electrode to be heated; power refers to the power of the heating device; efficiency refers to the thermal efficiency of the heating device;

[0024] The calculation formula for the theoretical value of electrode temperature change is:

[0025] ΔT 理论 =Q 理论 / (m×c)

[0026] Where, ΔT 理论 is the theoretical value of electrode temperature change; Q 理论 is the theoretical heat absorbed or released by the electrode; m is the mass of the electrode; c is the specific heat capacity of the electrode.

[0027] Furthermore, the process of correlating and analyzing the infrared thermal imaging detection data of the ladle of the historical heats and the corresponding molten steel temperature in the ladle to obtain the third heating temperature rise parameter of the heats includes:

[0028] T 钢水 =a×T 钢包 +b;

[0029] Among them, T 钢水 is the temperature of molten steel in the ladle; T 钢包 is the ladle body temperature; a is the first empirical coefficient; b is the first empirical coefficient;

[0030] Wherein, heating time detection value = detection heat / (power × efficiency);

[0031] The calculation formula of the electrode temperature change detection value is:

[0032] ΔT 检测 =Q 检测 / (m×c)

[0033] Where, ΔT 检测 is the electrode temperature change detection value; Q 检测 is the detected heat absorbed or released by the electrode; m is the mass of the electrode; c is the specific heat capacity of the electrode.

[0034] Furthermore, the process of obtaining infrared thermal imaging detection data of the ladle of historical furnaces includes: symmetrically installing a pair of high-temperature infrared thermal imaging thermometers on both sides of the ladle, and performing online real-time temperature detection on the ladle body during refining and heating treatment to obtain infrared thermal imaging detection data of the ladle of historical furnaces.

[0035] The present invention also proposes a heating and temperature-raising precision control system for a ladle refining furnace, comprising: a data acquisition module, a prediction module and a control module;

[0036] The data acquisition module is used to obtain the ladle data of historical furnaces and the relevant factors affecting the temperature of molten steel, and to build a historical furnace data information database; pre-process the heating temperature rise values ​​of historical furnaces under various conditions to deduce the first heating parameters of the furnace; perform power heat balance calculation based on the initial temperature of molten steel, target temperature of molten steel, heating temperature and heat loss during the heating process of historical furnaces to obtain the theoretical second heating parameters; perform correlation analysis on the infrared thermal imaging detection data of the ladle of historical furnaces and the corresponding molten steel temperature in the ladle to obtain the third heating parameters of the furnace;

[0037] The prediction module is used to input the first heating parameter, the second heating parameter and the third heating parameter into the input layer of the convolutional neural network, use the convolutional neural network to predict, and output the recommended fourth heating parameter through the output layer;

[0038] The control module is used to obtain the fifth heating temperature rise parameter of the current furnace, compare the fourth heating temperature rise parameter with the fifth heating temperature rise parameter to obtain the actual heating parameter of the current furnace, and realize precise control of the temperature of the current furnace according to the actual heating parameter of the current furnace.

[0039] The effects provided in the content of the invention are only the effects of the embodiments, not all the effects of the invention. One of the above technical solutions has the following advantages or beneficial effects:

[0040] The present invention proposes a method and system for accurately controlling the heating and temperature rise of a ladle refining furnace, the method comprising the following steps: obtaining ladle data of historical furnaces and relevant factors affecting the temperature of molten steel, and constructing a historical furnace data information database; pre-processing the heating and temperature rise values ​​of historical furnaces under various conditions to deduce the first heating and temperature rise parameters of the furnace; performing electric heat balance calculation according to the initial temperature of molten steel, target temperature of molten steel, heating temperature and heat loss during heating process of historical furnaces to obtain a theoretical second heating and temperature rise parameter; performing correlation analysis on infrared thermal imaging detection data of the ladle of historical furnaces and the corresponding molten steel temperature in the ladle to obtain the third heating and temperature rise parameter of the furnace; inputting the first heating and temperature rise parameter, the second heating and temperature rise parameter and the third heating and temperature rise parameter into the input layer of a convolutional neural network, using the convolutional neural network to predict, and outputting the recommended fourth heating and temperature rise parameter through the output layer; obtaining the fifth heating and temperature rise parameter of the current furnace, comparing the fourth heating and temperature rise parameter with the fifth heating and temperature rise parameter to obtain the actual heating parameter of the current furnace, and realizing accurate control of the temperature of the current furnace according to the actual heating parameter of the current furnace. Based on a method for accurately controlling the heating and temperature rise of a ladle refining furnace, a precise control system for heating and temperature rise of a ladle refining furnace is also proposed. The invention realizes precise control of the temperature of the furnace, significantly improves production efficiency and reduces production costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a flow chart of a method for accurately controlling the heating and temperature rise of a ladle refining furnace proposed in Example 1 of the present invention;

[0042] Figure 2 This is a schematic diagram of a heating and temperature rising precision control system for a ladle refining furnace proposed in Example 2 of the present invention. DETAILED DESCRIPTION

[0043] In order to clearly illustrate the technical features of the present solution, the present invention is described in detail below through specific implementation methods and in conjunction with the accompanying drawings. The disclosure below provides many different embodiments or examples for realizing different structures of the present invention. In order to simplify the disclosure of the present invention, the components and settings of specific examples are described below. In addition, the present invention may repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed. It should be noted that the components illustrated in the accompanying drawings are not necessarily drawn to scale. The present invention omits the description of known components and processing techniques and processes to avoid unnecessary limitations on the present invention.

[0044] Example 1

[0045] A method for accurately controlling the heating and temperature rise of a ladle refining furnace proposed in Example 1 of the present invention is used to solve the technical problems existing in the temperature control of a ladle refining furnace in the prior art. Figure 1 This is a flow chart of a method for accurately controlling the heating and temperature rise of a ladle refining furnace proposed in Example 1 of the present invention;

[0046] In step S1, the ladle data of historical heats and the relevant factors affecting the temperature of molten steel are obtained to build a historical heat data information database;

[0047] The relevant factors affecting the molten steel temperature include ladle life, ladle state, ladle bottom blowing permeability, ladle turnover, converter tapping temperature, ladle charging, LF process assistance and waiting time after tapping, refining charging and wire feeding, argon blowing and weak stirring time, refining electrode heating parameters of the corresponding furnace and the target temperature at the end of the treatment.

[0048] In step S2, the heating temperature values ​​of each conditional historical furnace are pre-processed to optimize the first heating parameter of the furnace; that is, the first heating parameter is F 推优值 , the first heating parameter F 推优值 Including heating time optimization value t 推优值 , and the current optimization value corresponding to the heating time optimization value I 推优值 And voltage optimization value U 推优值 .

[0049] Data preprocessing refers to some processing of data before the main processing. It is mainly to clean up outliers and correct erroneous data. In the real world, data is generally incomplete and inconsistent dirty data, which cannot be directly used for data mining, or the mining results are unsatisfactory. In order to improve the quality of data mining, data preprocessing technology has been developed. There are many methods for data preprocessing: data cleaning, data integration, data transformation, data reduction, etc. These data processing technologies are used before data mining, which greatly improves the quality of data mining models and reduces the time required for actual mining. For this case, it is to eliminate abnormal data with large deviations. After eliminating the abnormal data, linear regression analysis is performed to obtain the corresponding data with the highest probability under various conditions, which is the recommended data.

[0050] In step S3, the theoretical second heating parameter is obtained by performing power heat balance calculation based on the initial temperature of the molten steel, the target temperature of the molten steel, the heating temperature and the heat loss during the heating process of the historical furnace. The second heating parameter is F 理论值 , the second heating parameter F 理论值 Including the theoretical value of heating time t 理论值 , and the theoretical value of the current corresponding to the theoretical value of the heating time I 理论值 And the voltage theoretical value U 理论值 .

[0051] The process of obtaining the theoretical second heating temperature rise parameters by performing electric heat balance calculation based on the initial temperature of molten steel, target temperature of molten steel, heating temperature and heat loss during the heating process of the historical furnaces includes:

[0052] T 初始温度 -T 热损失 +T 加热温度 =T 目标温度 ;

[0053] Theoretical value of heating time = theoretical heat / (power × efficiency);

[0054] Wherein, heat refers to the theoretical heat capacity of the electrode to be heated; power refers to the power of the heating device; efficiency refers to the thermal efficiency of the heating device;

[0055] The calculation formula for the theoretical value of electrode temperature change is:

[0056] ΔT 理论 =Q 理论 / (m×c);

[0057] Where, ΔT 理论 is the theoretical value of electrode temperature change; Q 理论 is the theoretical heat absorbed or released by the electrode; m is the mass of the electrode; c is the specific heat capacity of the electrode.

[0058] In step S4, the infrared thermal imaging detection data of the ladle of the historical heat and the corresponding molten steel temperature in the ladle are correlated and analyzed to obtain the third heating temperature raising parameter of the heat;

[0059] A pair of high-temperature infrared thermal imaging thermometers are symmetrically installed on both sides of the ladle to perform online real-time temperature detection on the ladle body during refining and heating treatment. The thermal imaging function is correlated, compared and corrected with the corresponding molten steel temperature in the ladle.

[0060] The third heating parameter F 检测值 Including heating time detection value t 检测值 , and the current detection value I corresponding to the time detection value 检测值 And the voltage detection value U 检测值 .

[0061] The process of correlating and analyzing the infrared thermal imaging detection data of the ladle of the historical heat and the corresponding molten steel temperature in the ladle to obtain the third heating temperature rise parameters of the heat includes:

[0062] T 钢水 =a×T 钢包 +b;

[0063] Among them, T 钢水 is the temperature of molten steel in the ladle; T 钢包 is the ladle body temperature; a is the first empirical coefficient; b is the first empirical coefficient;

[0064] Wherein, heating time detection value = detection heat / (power × efficiency);

[0065] The calculation formula of the electrode temperature change detection value is:

[0066] ΔT 检测 =Q 检测 / (m×c)

[0067] Where, ΔT 检测 is the electrode temperature change detection value; Q 检测 is the detected heat absorbed or released by the electrode; m is the mass of the electrode; c is the specific heat capacity of the electrode.

[0068] In step S5, the first heating parameter F 推优值 , the second heating temperature parameter F 理论值 and the third heating temperature rise parameters are input into the input layer of the convolutional neural network.

[0069] In step S6, after prediction by the convolutional neural network, the recommended fourth heating temperature parameter F is output through the output layer. 推荐值 .

[0070] In step S7, the fifth heating temperature rise parameter of the current furnace is obtained, and the fourth heating temperature rise parameter F推荐值 Compare with the fifth heating temperature parameter to get the actual heating parameter F of the current furnace 实际值 , and accurately control the current furnace temperature according to the actual heating parameters of the current furnace.

[0071] The process of achieving precise control of the current furnace temperature according to the comparison results includes: when the actual heating parameter is greater than the fourth heating temperature rise parameter, the heating speed is reduced by reducing the heating power; when the actual heating parameter is less than the fourth heating temperature rise parameter, the heating speed is increased by increasing the heating power.

[0072] The data detected by thermal imaging and the F corresponding to a certain moment in the heating process 推荐值 The results are compared with the data, that is, the infrared thermal imaging detection temperature at a certain moment during the heating process is greater than F 推荐值 If the temperature is less than F, it means the heating speed is too fast. The adjustment correction is to reduce the heating power and the heating speed. On the contrary, if the infrared thermal imaging temperature is less than F at a certain moment in the heating process, 推荐值 When the temperature value is too high, it means that the heating speed is too high. The adjustment correction at this time is to increase the heating power and speed up the heating speed.

[0073] In step S8, after the fourth heating temperature rise parameter is compared with the fifth heating temperature rise parameter to obtain the actual heating parameter of the current furnace, the actual temperature of the current furnace is obtained according to the actual heating parameter of the current furnace.

[0074] In order to fully illustrate the process of implementing the method for accurately controlling the heating and temperature rise of a ladle refining furnace proposed in Example 1 of the present invention, the following specific example 1 is described in detail.

[0075] Various temperature influencing factors of a certain furnace 1: the life of the ladle is the 7th furnace, there is no residue in the ladle, the minor repair ladle is the 2nd furnace, the bottom blowing permeability of the ladle is good, the ladle turnover is normal, the converter tapping temperature is 1636℃, the amount of ladle modifier added is 0.35kg per ton of steel, the time interval for tapping and lifting to LF is <10min, and the LF arrival temperature is 1602℃.

[0076] The refining charging and wire feeding are both the planned target requirements for the steel grade. The argon blowing and weak stirring time are 28 minutes. The temperature after refining charging and argon blowing is 1568℃, and the target temperature requirement at the end of the treatment is 1582℃.

[0077] According to the heating parameters of historical furnaces with the same or similar conditions in the database, the model optimizes and calculates F 推优值 Voltage: 260V; Current: 45KA; Heating time: 3min20s.

[0078] Calculation of electrode heating temperature parameter F using thermal balance theory 理论值Voltage: 260V; Current: 45KA; Heating time: 3min15s.

[0079] The electrode heating parameter F of this furnace is calculated from the temperature change curve detected by the high-temperature infrared thermal imaging thermometer 检测值 Voltage: 260V; Current: 45KA; Heating time: 3min18s.

[0080] The model recommended heating parameter F under the information conditions of this furnace calculated by the recurrent neural network 推荐值 Voltage: 260V; Current: 45KA; Heating time: 3min18s. 推荐值 During the heating treatment, the temperature detected by the high-temperature infrared thermal imaging thermometer was consistent with the temperature change curve in the model. After heating for 3 minutes and 18 seconds, the actual measured temperature was 1582°C, accurately hitting the target temperature.

[0081] In order to fully illustrate the process of implementing the method for accurately controlling the heating and temperature rise of a ladle refining furnace proposed in Example 1 of the present invention, the following specific example 2 is described in detail.

[0082] Various temperature influencing factors of a certain furnace 2: the life of the ladle is the 11th furnace, there is no residue in the ladle, the bottom blowing permeability of the ladle is good, the ladle turnover is normal, the converter tapping temperature is 1645℃, the amount of ladle modifier added is 0.30kg per ton of steel, the time interval for tapping and lifting to LF is <10min, and the LF arrival temperature is 1612℃.

[0083] The refining charging and wire feeding are both the planned target requirements for the steel grade. The argon blowing and weak stirring time is 22 minutes. The refining charging is 0.45kg per ton of steel. The temperature after uniform argon blowing is 1562℃. The target temperature requirement at the end of the treatment is 1586℃.

[0084] According to the heating parameters of historical furnaces with the same or similar conditions in the database, the model optimizes and calculates F 推优值 Voltage: 260V; Current: 50KA; Heating time: 4min32s.

[0085] Calculation of electrode heating temperature parameter F using thermal balance theory 理论值 Voltage: 260V; Current: 50KA; Heating time: 4min25s.

[0086] The electrode heating parameter F of this furnace is calculated from the temperature change curve detected by the high-temperature infrared thermal imaging thermometer 检测值 Voltage: 260V; Current: 50KA; Heating time: 4min30s.

[0087] The model recommended heating parameter F under the information conditions of this furnace calculated by the recurrent neural network 推荐值Voltage: 260V; Current: 50KA; Heating time: 4min30s.

[0088] According to F 推荐值 Perform heating treatment, compare the temperature detected by the high-temperature infrared thermal imaging thermometer with the temperature change curve in the model and correct it for 2s, then press F 实际值 (voltage: 260V; current: 50KA; heating time 4min28s) heating, the actual measured temperature is 1586℃, accurately hitting the target temperature.

[0089] A method for accurately controlling the heating and temperature rise of a ladle refining furnace proposed in Example 1 of the present invention establishes a database by collecting data on the ladles / molten steel of historical furnaces and various related factors affecting the temperature of the molten steel, and then performs data preprocessing and big data analysis. The data optimization calculation, heat balance theory calculation, and high-temperature infrared thermal imaging thermometer process detection data are subjected to recurrent neural network calculation, and compared and corrected in combination with the information of this furnace and the real-time detection information, and finally the actual heating parameter F actual value of this furnace is obtained, thereby realizing accurate control of the temperature of this furnace, significantly improving production efficiency and reducing production costs.

[0090] Example 2

[0091] Based on the heating and temperature rise precision control method of a ladle refining furnace proposed in Example 1 of the present invention, Example 2 of the present invention further proposes a heating and temperature rise precision control system of a ladle refining furnace. Figure 2 This is a schematic diagram of a heating and temperature rise precision control system for a ladle refining furnace proposed in Example 2 of the present invention, the system comprising: a data acquisition module, a prediction module and a control module;

[0092] The data acquisition module is used to obtain the ladle data of historical furnaces and the relevant factors affecting the temperature of molten steel, and to build a historical furnace data information database; pre-process the heating and temperature rise values ​​of historical furnaces under various conditions to deduce the first heating and temperature rise parameters of the furnace; perform power heat balance calculation based on the initial temperature of molten steel, target temperature of molten steel, heating temperature and heat loss during the heating process of historical furnaces to obtain the theoretical second heating and temperature rise parameters; perform correlation analysis on the infrared thermal imaging detection data of the ladle of historical furnaces and the corresponding molten steel temperature in the ladle to obtain the third heating and temperature rise parameters of the furnace;

[0093] The prediction module is used to input the first heating parameter, the second heating parameter and the third heating parameter into the input layer of the convolutional neural network, use the convolutional neural network to predict, and output the recommended fourth heating parameter through the output layer;

[0094] The control module is used to obtain the fifth heating temperature rise parameter of the current furnace, compare the fourth heating temperature rise parameter with the fifth heating temperature rise parameter to obtain the actual heating parameter of the current furnace, and realize precise control of the temperature of the current furnace according to the actual heating parameter of the current furnace.

[0095] The process executed by the data acquisition module includes: the relevant factors affecting the molten steel temperature include ladle life, ladle status, ladle bottom blowing permeability, ladle turnover, converter tapping temperature, ladle charging, LF process assistance and waiting time after tapping, refining charging and wire feeding, argon blowing and weak stirring time, refining electrode heating parameters of the corresponding furnace and the target temperature at the end of the treatment.

[0096] The first temperature rise heating parameter includes a heating time optimal value, and a current optimal value and a voltage optimal value corresponding to the heating time optimal value; the first temperature rise heating parameter includes a heating time theoretical value, and a current theoretical value and a voltage theoretical value corresponding to the heating time theoretical value; the third temperature rise heating parameter includes a heating time detection value, and a current detection value and a voltage detection value corresponding to the time detection value.

[0097] The process of pre-processing the heating temperature rise values ​​of the historical furnaces under various conditions to deduce the first heating temperature rise parameters of the furnaces includes: performing abnormal cleaning on the heating temperature rise values ​​of the historical furnaces under various conditions, eliminating abnormal data and then performing linear regression analysis to obtain the corresponding data with the highest probability under various conditions, that is, the first heating temperature rise parameters.

[0098] The process of obtaining the theoretical second heating temperature rise parameters by performing electric heat balance calculation based on the initial temperature of molten steel, target temperature of molten steel, heating temperature and heat loss during the heating process of the historical furnaces includes:

[0099] T 初始温度 -T 热损失 +T 加热温度 =T 目标温度 ;

[0100] Theoretical value of heating time = theoretical heat / (power × efficiency);

[0101] Wherein, heat refers to the theoretical heat capacity of the electrode to be heated; power refers to the power of the heating device; efficiency refers to the thermal efficiency of the heating device;

[0102] The calculation formula for the theoretical value of electrode temperature change is:

[0103] ΔT 理论 =Q 理论 / (m×c);

[0104] Where, ΔT 理论 is the theoretical value of electrode temperature change; Q 理论is the theoretical heat absorbed or released by the electrode; m is the mass of the electrode; c is the specific heat capacity of the electrode.

[0105] The process of correlating and analyzing the infrared thermal imaging detection data of the ladle of the historical heat and the corresponding molten steel temperature in the ladle to obtain the third heating temperature rise parameters of the heat includes:

[0106] T 钢水 =a×T 钢包 +b;

[0107] Among them, T 钢水 is the temperature of molten steel in the ladle; T 钢包 is the ladle body temperature; a is the first empirical coefficient; b is the first empirical coefficient;

[0108] Wherein, heating time detection value = detection heat / (power × efficiency);

[0109] The calculation formula of the electrode temperature change detection value is:

[0110] ΔT 检测 =Q 检测 / (m×c);

[0111] Where, ΔT 检测 is the electrode temperature change detection value; Q 检测 is the detected heat absorbed or released by the electrode; m is the mass of the electrode; c is the specific heat capacity of the electrode.

[0112] The process of obtaining infrared thermal imaging detection data of the ladle of historical heats includes: symmetrically installing a pair of high-temperature infrared thermal imaging thermometers on both sides of the ladle, and performing online real-time temperature detection on the ladle body during refining and heating treatment to obtain infrared thermal imaging detection data of the ladle of historical heats.

[0113] The prediction module uses a convolutional neural network, which generally includes an input layer, a hidden layer, and an output layer.

[0114] During the execution of the control module, after the fourth heating temperature rise parameter is compared with the fifth heating temperature rise parameter to obtain the actual heating parameter of the current furnace, it also includes obtaining the actual temperature of the current furnace according to the actual heating parameter of the current furnace.

[0115] The process of achieving precise control of the current furnace temperature according to the comparison results includes: when the actual heating parameter is greater than the fourth heating temperature rise parameter, the heating speed is reduced by reducing the heating power; when the actual heating parameter is less than the fourth heating temperature rise parameter, the heating speed is increased by increasing the heating power.

[0116] A precise control system for heating and temperature rise of a ladle refining furnace proposed in Example 2 of the present invention establishes a database by collecting data on the ladles / molten steel of historical furnaces and various related factors affecting the temperature of the molten steel, and then performs data preprocessing and big data analysis. The data is subjected to recurrent neural network calculations on data optimization calculations, heat balance theory calculations, and process detection data of high-temperature infrared thermal imaging thermometers. The data are compared and corrected in combination with the information of the current furnace and the real-time detection information, and finally the actual heating parameter F actual value of the current furnace is obtained, thereby achieving precise control of the temperature of the current furnace, significantly improving production efficiency, and reducing production costs.

[0117] The description of the relevant parts of a precise control system for heating and temperature rise of a ladle refining furnace provided in Example 2 of the present application can be found in the detailed description of the corresponding parts of a precise control method for heating and temperature rise of a ladle refining furnace provided in Example 1 of the present application, and will not be repeated here.

[0118] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the term "include", "comprise" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or equipment that includes a series of elements are inherent to the elements. In the absence of more restrictions, the elements limited by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or equipment that includes the elements. In addition, the above-mentioned technical solution provided in the embodiment of the present application is consistent with the corresponding technical solution in the prior art in principle, and the part is not described in detail, so as not to repeat too much.

[0119] Although the above describes the specific implementation of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. For those skilled in the art, other different forms of modifications or deformations can be made on the basis of the above description. It is not necessary and impossible to list all the implementation methods here. On the basis of the technical solution of the present invention, various modifications or deformations that can be made by those skilled in the art without creative work are still within the scope of protection of the present invention.

Claims

1. A method for accurately controlling the heating temperature of a ladle refining furnace, characterized in that: The following steps are involved: Obtain the ladle data of historical furnaces and the relevant factors affecting the temperature of molten steel, and build a historical furnace data information database; pre-process the heating and temperature rise values ​​of historical furnaces under various conditions to deduce the first heating and temperature rise parameters of the furnace; perform power heat balance calculation based on the initial temperature of molten steel, target temperature of molten steel, heating temperature and heat loss during the heating process of historical furnaces to obtain the theoretical second heating and temperature rise parameters; perform correlation analysis on the infrared thermal imaging detection data of the ladle of historical furnaces and the corresponding molten steel temperature in the ladle to obtain the third heating and temperature rise parameters of the furnace; Inputting the first heating parameter, the second heating parameter and the third heating parameter into the input layer of the convolutional neural network, using the convolutional neural network to predict, and outputting the recommended fourth heating parameter through the output layer; Obtain the fifth heating temperature rise parameter of the current furnace, compare the fourth heating temperature rise parameter with the fifth heating temperature rise parameter to obtain the actual heating parameter of the current furnace, and realize accurate control of the temperature of the current furnace according to the actual heating parameter of the current furnace.

2. The method for accurately controlling the heating temperature rise of a ladle refining furnace according to claim 1, characterized in that: After comparing the fourth heating temperature rise parameter with the fifth heating temperature rise parameter to obtain the actual heating parameter of the current furnace, the method further includes obtaining the actual temperature of the current furnace according to the actual heating parameter of the current furnace.

3. The method for accurately controlling the heating temperature rise of a ladle refining furnace according to claim 1, characterized in that: The process of achieving accurate control of the current furnace temperature according to the comparison result includes: When the actual heating parameter is greater than the fourth heating temperature rise parameter, the heating speed is reduced by reducing the heating power; When the actual heating parameter is less than the fourth heating temperature rise parameter, the heating speed is increased by increasing the heating power.

4. The method for accurately controlling the heating temperature rise of a ladle refining furnace according to claim 1, characterized in that: The relevant factors affecting the molten steel temperature include ladle life, ladle state, ladle bottom blowing permeability, ladle turnover, converter tapping temperature, ladle charging, LF process assistance and waiting time after tapping, refining charging and wire feeding, argon blowing and weak stirring time, refining electrode heating parameters of the corresponding furnace and the target temperature at the end of the treatment.

5. The method for accurately controlling the heating temperature rise of a ladle refining furnace according to claim 1, characterized in that: The first temperature rise heating parameter includes a heating time optimal value, and a current optimal value and a voltage optimal value corresponding to the heating time optimal value; The first temperature rise heating parameter includes a heating time theoretical value, and a current theoretical value and a voltage theoretical value corresponding to the heating time theoretical value; The third temperature rise heating parameter includes a heating time detection value, and a current detection value and a voltage detection value corresponding to the time detection value.

6. The method for accurately controlling the heating and temperature rise of a ladle refining furnace according to claim 5, characterized in that: The process of pre-processing the heating temperature rise values ​​of the historical furnaces under various conditions to deduce the first heating temperature rise parameters of the furnaces includes: performing abnormal cleaning on the heating temperature rise values ​​of the historical furnaces under various conditions, eliminating abnormal data and then performing linear regression analysis to obtain the corresponding data with the highest probability under various conditions, that is, the first heating temperature rise parameters.

7. The method for accurately controlling the heating temperature rise of a ladle refining furnace according to claim 5, characterized in that: The process of performing electric heat balance calculation to obtain the theoretical second heating temperature rise parameter according to the initial temperature of molten steel, target temperature of molten steel, heating temperature and heat loss during the heating process of the historical furnaces includes: T 初始温度 -T 热损失 +T 加热温度 =T 目标温度 ; Theoretical value of heating time = theoretical heat / (power × efficiency); Wherein, heat refers to the theoretical heat capacity of the electrode to be heated; power refers to the power of the heating device; efficiency refers to the thermal efficiency of the heating device; The calculation formula for the theoretical value of electrode temperature change is: ΔT 理论 =Q 理论 / (m×c); Where, ΔT 理论 is the theoretical value of electrode temperature change; Q 理论 is the theoretical heat absorbed or released by the electrode; m is the mass of the electrode; c is the specific heat capacity of the electrode.

8. The method for accurately controlling the heating temperature rise of a ladle refining furnace according to claim 5, characterized in that: The process of correlating and analyzing the infrared thermal imaging detection data of the ladle of the historical heat and the corresponding molten steel temperature in the ladle to obtain the third heating temperature rise parameters of the heat includes: T 钢水 =a×T 钢包 +b; Among them, T 钢水 is the temperature of molten steel in the ladle; T 钢包 is the ladle body temperature; a is the first empirical coefficient; b is the first empirical coefficient; Wherein, heating time detection value = detection heat / (power × efficiency); The calculation formula of the electrode temperature change detection value is: ΔT 检测 =Q 检测 / (m×c); Where, ΔT 检测 is the electrode temperature change detection value; Q 检测 is the detected heat absorbed or released by the electrode; m is the mass of the electrode; c is the specific heat capacity of the electrode.

9. The method for accurately controlling the heating and temperature rise of a ladle refining furnace according to claim 1, characterized in that: The process of obtaining infrared thermal imaging detection data of the ladle of historical heats includes: symmetrically installing a pair of high-temperature infrared thermal imaging thermometers on both sides of the ladle, and performing online real-time temperature detection on the ladle body during refining and heating treatment to obtain infrared thermal imaging detection data of the ladle of historical heats.

10. A heating and temperature rising precision control system for a ladle refining furnace, characterized in that: include: Data acquisition module, prediction module and control module; The data acquisition module is used to obtain the ladle data of historical furnaces and the relevant factors affecting the temperature of molten steel, and to build a historical furnace data information database; pre-process the heating temperature rise values ​​of historical furnaces under various conditions to deduce the first heating parameters of the furnace; perform power heat balance calculation based on the initial temperature of molten steel, target temperature of molten steel, heating temperature and heat loss during the heating process of historical furnaces to obtain the theoretical second heating parameters; perform correlation analysis on the infrared thermal imaging detection data of the ladle of historical furnaces and the corresponding molten steel temperature in the ladle to obtain the third heating parameters of the furnace; The prediction module is used to input the first heating parameter, the second heating parameter and the third heating parameter into the input layer of the convolutional neural network, use the convolutional neural network to predict, and output the recommended fourth heating parameter through the output layer; The control module is used to obtain the fifth heating temperature rise parameter of the current furnace, compare the fourth heating temperature rise parameter with the fifth heating temperature rise parameter to obtain the actual heating parameter of the current furnace, and realize precise control of the temperature of the current furnace according to the actual heating parameter of the current furnace.

Images