Top-bottom combined blown converter smelting monitoring method, system, equipment and medium

Abstract

The invention discloses a top-bottom combined blowing converter smelting monitoring method, system and equipment and a medium, mainly relates to the technical field of converter smelting, and is used for solving the problems that manual errors exist, the labor intensity is high, and the control opportunities of converter bottom blowing operation, oxygen lance control, feeding and the like are not accurate enough in an existing production mode of manual control. Comprising the following steps: acquiring furnace historical data in a historical time period; based on a preset secondary branch number, dividing the heat historical data in the historical time period into a preset secondary branch number of secondary sets; taking the secondary sets as training data, and training a preset artificial intelligence algorithm to obtain trained models corresponding to the secondary sets; based on a preset acquisition time point, acquiring current heat detection data; determining a second set corresponding to the current heat detection data; and inputting the current heat detection data into the trained model corresponding to the second set, so as to obtain the current converter bottom blowing operation information, the oxygen lance control position and the charging condition.

Description

Technical Field

[0001] The present application relates to the technical field of converter smelting, and particularly to a monitoring method, system, device and medium for top-bottom combined blowing converter smelting. Background Art

[0002] Converter steelmaking uses hot metal, scrap steel, and ferroalloys as the main raw materials. Without relying on external energy, the steelmaking process is completed in the converter by the physical heat of the molten iron itself and the chemical reactions between the components of the molten iron. Converter steelmaking production is the top priority in the steel production process and occupies an important production position. Due to its fast production speed, large output, high single-furnace output, low cost, and low investment, it is the most widely used steelmaking equipment and is being widely applied and promoted under the influence of the continuous development of the economy and society.

[0003] Efficient converter smelting involves multiple smelting process flows. The realization process of the smelting process flow mainly relies on manual control of the bottom blowing operation of the converter, oxygen lance control, and batching at present.

[0004] However, the above traditional production method using manual control has errors caused by manual calculation and high labor intensity for workers. In addition, in the context of high-efficiency blowing, with the rapid heating of the converter bath and slag formation, the control difficulty of the double hit rate of carbon and temperature at the end of converter blowing increases, which also increases the risks of abnormal furnace conditions, splashing, and back-drying. Therefore, there is an urgent need for a monitoring method, system, device and medium for top-bottom combined blowing converter smelting to solve the problems of manual errors, high labor intensity for workers, and inaccurate control timing of bottom blowing operation, oxygen lance control, batching, etc. in the above production method using manual control. Summary of the Invention

[0005] In view of the above deficiencies of the prior art, the present application provides a monitoring method, system, device and medium for top-bottom combined blowing converter smelting to solve the problems of manual errors, high labor intensity for workers, and inaccurate control timing of bottom blowing operation, oxygen lance control, batching, etc. in the existing production method using manual control.

[0006] In the first aspect, the present application provides a monitoring method for top-bottom combined blowing converter smelting, and the method includes: Obtain the heat history data within a historical time period; wherein, the heat history data at least includes: charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, LIBs detection results, converter bottom blowing operation information, oxygen lance control position, charging situation; based on a preset number of secondary branches, divide the heat history data within the historical time period into a preset number of secondary branches of secondary sets; use the secondary sets as training data to train a preset artificial intelligence algorithm to obtain a trained model corresponding to each secondary set; based on a preset acquisition time point, obtain the current heat detection data, wherein the current heat detection data at least includes: charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, LIBs detection results; determine the second set corresponding to the current heat detection data; then input the current heat detection data into the trained model corresponding to the second set to obtain the current converter bottom blowing operation information, oxygen lance control position, and charging situation.

[0007] Further, before obtaining the current heat detection data, the method further includes: Real-time detect the oxygen lance gravity through a force sensor installed on the steel wire rope or rope pulley suspending the oxygen lance, and then obtain the oxygen lance gravity data; obtain the converter furnace mouth flame image, and through an image recognition model, identify the furnace mouth flame information corresponding to the converter furnace mouth flame image; wherein, the furnace mouth flame information at least includes: flame color, brightness, texture.

[0008] Further, determining the second set corresponding to the current heat detection data specifically includes: Extract 10 pieces of heat history data from each second set as standard data; use the charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, LIBs detection results in the heat history data of the standard data as input data; input the input data and the current heat detection data into the KNN algorithm to obtain the name of the second set of the input data in the cluster where the current heat detection data is located; determine the second set name with the most occurrences as the second set corresponding to the current heat detection data.

[0009] Further, based on a preset number of secondary branches, dividing the heat history data within the historical time period into a preset number of secondary branches of secondary sets specifically includes: Perform clustering of the heat history data using the KNN algorithm according to the charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, LIBs detection results in the heat history data; wherein, K = preset number of secondary branches in the KNN algorithm; obtain a preset number of clustering sets, and determine the clustering sets as secondary sets.

[0010] In a second aspect, the present application provides a top-bottom combined blowing converter smelting monitoring system, which includes: An acquisition module, configured to acquire the historical data of the heats within a historical time period; wherein, the historical data of the heats at least includes: charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, LIBs detection results, bottom blowing operation information of the converter, oxygen lance control position, and charging situation; a division module, configured to divide the historical data of the heats within the historical time period into a preset number of second-level sets based on the preset number of second-level branches; an obtaining module, configured to use the second-level sets as training data to train a preset artificial intelligence algorithm to obtain a trained model corresponding to each second-level set; and is further configured to acquire the current heat detection data based on a preset acquisition time point, wherein the current heat detection data at least includes: charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, LIBs detection results; determine a second set corresponding to the current heat detection data; and then input the current heat detection data into the trained model corresponding to the second set to obtain the current bottom blowing operation information of the converter, oxygen lance control position, and charging situation.

[0011] Further, the system further includes a collection module, configured to perform real-time detection of the oxygen lance gravity through a force sensor installed on the steel wire rope or rope pulley suspending the oxygen lance, so as to obtain the oxygen lance gravity data; Acquire an image of the furnace mouth flame of the converter, and identify the furnace mouth flame information corresponding to the image of the furnace mouth flame of the converter through an image recognition model; wherein, the furnace mouth flame information at least includes: flame color, brightness, and texture.

[0012] Further, the division module includes a first division unit, configured to perform clustering on the historical data of the heats according to the charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, and LIBs detection results in the historical data of the heats by using the KNN algorithm; wherein, K in the KNN algorithm = the preset number of second-level branches; obtain a preset number of clustering sets, and determine the clustering sets as the second-level sets.

[0013] Further, the obtaining module includes a second division unit, configured to extract 10 pieces of historical data of the heats from each second-level set as standard data; use the charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, and LIBs detection results in the historical data of the heats in the standard data as input data; input the input data and the current heat detection data into the KNN algorithm to obtain the name of the second-level set of the input data in the clustering where the current heat detection data is located; and determine the name of the second-level set with the most occurrences as the second-level set corresponding to the current heat detection data.

[0014] In a third aspect, the present application provides a top and bottom combined blowing converter smelting monitoring device, which includes: a processor; and a memory storing executable code thereon. When the executable code is executed, the processor is caused to execute a top and bottom combined blowing converter smelting monitoring method as described in any one of the above.

[0015] In a fourth aspect, the present application provides a non-volatile computer storage medium storing computer instructions thereon. When the computer instructions are executed, a top and bottom combined blowing converter smelting monitoring method as described in any one of the above is implemented.

[0016] Those skilled in the art can understand that the present application has at least the following beneficial effects: The present application discloses a top and bottom combined blowing converter smelting monitoring method, system, device and medium. By dividing the furnace historical data in a historical time period into a preset number of second-level branches of second-level sets, and then using the second-level sets as training data to obtain trained models corresponding to each second-level set, the model is trained with relatively concentrated data in a small range, improving the accuracy of the model, and further improving the accuracy of subsequent prediction of control timings such as bottom blowing operation, oxygen lance control, and feeding of the converter. In addition, the present application can be automatically implemented, solving the problems of manual error and high labor intensity of workers in the production method of manual control in the existing solutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The following describes some embodiments of the present disclosure with reference to the drawings, in which: Figure 1 is a flowchart of a top and bottom combined blowing converter smelting monitoring method provided by an embodiment of the present application.

[0018] Figure 2 is an internal structure schematic diagram of a top and bottom combined blowing converter smelting monitoring system provided by an embodiment of the present application.

[0019] Figure 3 is an internal structure schematic diagram of a top and bottom combined blowing converter smelting monitoring device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] Those skilled in the art should understand that the embodiments described below are only the preferred embodiments of the present disclosure, and do not mean that the present disclosure can only be implemented through these preferred embodiments. These preferred embodiments are only used to explain the technical principles of the present disclosure and are not used to limit the protection scope of the present disclosure. Based on the preferred embodiments provided by the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative efforts should still fall within the protection scope of the present disclosure.

[0021] It should also be noted that the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, commodity or device including the element.

[0022] The technical solutions proposed in the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0023] The embodiments of the present application provide a top and bottom combined blowing converter smelting monitoring method, as Figure 1 shown, the method provided by the embodiments of the present application mainly includes the following steps: Step 110: Obtain the historical data of the furnace charges within a historical time period.

[0024] It should be noted that the historical data of the furnace charges at least includes: charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, LIBs detection results, bottom blowing operation information of the converter, oxygen lance control position, and charging situation.

[0025] Among them, the charging conditions can be specifically: the temperature of the hot metal entering the furnace is 1386°C, and the hot metal composition is C: 4.40%; Si: 0.65%; Mn: 0.35%; P: 0.082; S: 0.028%; the addition amount of scrap + hot metal is (180 + 51) t, etc. The LIBs detection results can be specifically: the contents of CaO, SiO2, MgO, and FeO in the slag and the main component of the molten steel is the C content. The acquisition schemes of the bottom blowing operation information of the converter, the oxygen lance control position, and the charging situation are mainly the data input during the historical process. The oxygen lance gravity is detected in real time by a force sensor installed on the steel wire rope or rope wheel suspending the oxygen lance, and then the oxygen lance gravity data is obtained; the furnace mouth flame image of the converter is obtained, and through an image recognition model, the furnace mouth flame information corresponding to the furnace mouth flame image of the converter is recognized; among them, the furnace mouth flame information at least includes: flame color, brightness, and texture. The slag height can be obtained by a high-temperature and high-definition slag height (slag level) detection device inside the tapping hole. The sublance measurement results are mainly information such as temperature and carbon content. The flue gas data is mainly the CO content in the flue gas.

[0026] Step 120: Divide the historical data of the furnace charges within the historical time period into a preset number of second-level sets based on the preset number of second-level branches.

[0027] It should be noted that the preset number of secondary branches and the preset secondary branches can be determined by those skilled in the art according to actual needs. The purpose here in this application is to subdivide the historical data of furnace heats.

[0028] As an example, this step can be specifically as follows: According to the charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, and LIBs detection results in the historical data of furnace heats, perform clustering on the historical data of furnace heats using the KNN algorithm; where, in the KNN algorithm, K = the preset number of secondary branches; obtain the preset number of secondary branches of clustering sets, and determine the clustering sets as the secondary sets.

[0029] Step 130: Use the secondary sets as training data to train the preset artificial intelligence algorithm to obtain the trained models corresponding to each secondary set.

[0030] It should be noted that the preset artificial intelligence algorithm can be a convolutional neural network algorithm. Among them, the process of training the convolutional neural network algorithm can be realized by the existing technology, and this application does not limit it.

[0031] Step 140: Based on the preset acquisition time point, acquire the current furnace heat detection data.

[0032] It should be noted that the furnace heat detection data at least includes: charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, and LIBs detection results.

[0033] Step 150: Determine the second set corresponding to the current furnace heat detection data; then input the current furnace heat detection data into the trained model corresponding to the second set, and then obtain the current converter bottom blowing operation information, oxygen lance control position, and charging situation.

[0034] Among them, determining the second set corresponding to the current furnace heat detection data can be specifically as follows: Extract 10 pieces of historical data of furnace heats from each second set as standard data; use the charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, and LIBs detection results in the historical data of furnace heats in the standard data as input data; input the input data and the current furnace heat detection data into the KNN algorithm to obtain the name of the second set of the input data in the cluster where the current furnace heat detection data is located; determine the name of the second set with the most occurrences as the second set corresponding to the current furnace heat detection data.

[0035] In addition, Figure 2 This is a top-bottom combined blowing converter smelting monitoring system provided by an embodiment of this application. As Figure 2 shown, the system provided by the embodiment of this application mainly includes: An acquisition module 210 is used to acquire the historical data of heats within a historical time period; wherein, the historical data of heats at least includes: charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, LIBs detection results, converter bottom blowing operation information, oxygen lance control position, and charging situation.

[0036] A division module 220 is used to divide the historical data of heats within a historical time period into a preset number of second-level sets based on a preset number of second-level branches.

[0037] The division module 220 includes a first division unit, which is used to perform clustering on the historical data of heats by using the KNN algorithm according to the charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, and LIBs detection results in the historical data of heats; wherein, K in the KNN algorithm = the preset number of second-level branches; obtain a preset number of second-level branches of clustering sets, and determine the clustering sets as second-level sets.

[0038] An obtaining module 230 is used to use the second-level sets as training data to train a preset artificial intelligence algorithm to obtain trained models corresponding to each second-level set; and is also used to acquire the current heat detection data based on a preset acquisition time point, wherein the heat detection data at least includes: charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, and LIBs detection results; determine the second set corresponding to the current heat detection data; and then input the current heat detection data into the trained model corresponding to the second set, and further obtain the current converter bottom blowing operation information, oxygen lance control position, and charging situation.

[0039] The obtaining module 230 includes a second division unit, which is used to extract 10 pieces of historical data of heats from each second-level set as standard data; use the charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, and LIBs detection results in the historical data of heats in the standard data as input data; input the input data and the current heat detection data into the KNN algorithm to obtain the name of the second-level set of the input data in the cluster where the current heat detection data is located; and determine the name of the second-level set with the most occurrences as the second-level set corresponding to the current heat detection data.

[0040] The system further includes a collection module, which is used to perform real-time detection of the oxygen lance gravity through a force sensor installed on the wire rope or rope wheel for hanging the oxygen lance, and further obtain the oxygen lance gravity data; acquire the converter furnace mouth flame image, and identify the furnace mouth flame information corresponding to the converter furnace mouth flame image through an image recognition model; wherein, the furnace mouth flame information at least includes: flame color, brightness, and texture.

[0041] The above is the method embodiment in the present application. Based on the same inventive concept, the embodiment of the present application also provides an intelligent index report calculation and generation device. As Figure 3 shown, the device includes: a processor; and a memory, on which executable code is stored. When the executable code is executed, the processor is caused to execute an intelligent index report calculation and generation method as in the above embodiment.

[0042] Specifically, the server side obtains the furnace history data within a historical time period; wherein, the furnace history data at least includes: charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, LIBs detection results, converter bottom blowing operation information, oxygen lance control position, charging situation; based on the preset number of secondary branches, the furnace history data within the historical time period is divided into a preset number of secondary branches of secondary sets; the secondary sets are used as training data to train a preset artificial intelligence algorithm to obtain trained models corresponding to each secondary set; based on the preset acquisition time point, current furnace detection data is obtained, wherein the furnace detection data at least includes: charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, LIBs detection results; a second set corresponding to the current furnace detection data is determined; and then the current furnace detection data is input into the trained model corresponding to the second set, and then the current converter bottom blowing operation information, oxygen lance control position, and charging situation are obtained.

[0043] In addition, the embodiment of the present application also provides a non-volatile computer storage medium, on which executable instructions are stored. When the executable instructions are executed, an intelligent index report calculation and generation method as described above is implemented.

[0044] So far, the technical solutions of the present disclosure have been described in combination with multiple foregoing embodiments. However, it is easy for those skilled in the art to understand that the protection scope of the present disclosure is not limited to these specific embodiments. Without departing from the technical principle of the present disclosure, those skilled in the art can split and combine the technical solutions in the above various embodiments, and can also make equivalent changes or replacements to the relevant technical features. Any changes, equivalent replacements, improvements, etc. made within the technical concept and / or technical principle of the present disclosure will fall within the protection scope of the present disclosure.

Claims

1. A method for monitoring the smelting process of a top and bottom combined blown converter, characterized in that, The method includes: Obtaining the historical data of heats within a historical time period; wherein, the historical data of heats at least includes: charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, LIBs detection results, converter bottom blowing operation information, oxygen lance control position, charging situation; Dividing the historical data of heats within the historical time period into a preset number of second-level sets based on the preset number of second-level branches; Using the second-level sets as training data to train a preset artificial intelligence algorithm to obtain trained models corresponding to the respective second-level sets; Obtaining the current heat detection data based on a preset acquisition time point, wherein the current heat detection data at least includes: charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, LIBs detection results; Determining the second set corresponding to the current heat detection data; then inputting the current heat detection data into the trained model corresponding to the second set to obtain the current converter bottom blowing operation information, oxygen lance control position, and charging situation.

2. The top-bottom combined blowing converter smelting monitoring method according to claim 1, wherein Before obtaining the current heat detection data, the method further includes: Realtime detecting the oxygen lance gravity through a force sensor installed on the steel wire rope or rope pulley suspending the oxygen lance to obtain the oxygen lance gravity data; Obtaining a converter furnace mouth flame image and identifying the furnace mouth flame information corresponding to the converter furnace mouth flame image through an image recognition model; wherein, the furnace mouth flame information at least includes: flame color, brightness, texture.

3. The top-bottom combined blowing converter smelting monitoring method according to claim 1, characterized in that Determining the second set corresponding to the current heat detection data specifically includes: Extracting 10 pieces of historical data of heats from each second-level set as standard data; Using the charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, and LIBs detection results in the historical data of heats in the standard data as input data; Inputting the input data and the current heat detection data into the KNN algorithm to obtain the name of the second-level set of the input data in the cluster where the current heat detection data is located; determining the name of the second-level set with the most occurrences as the second-level set corresponding to the current heat detection data.

4. The top-bottom combined blowing converter smelting monitoring method according to claim 1, characterized in that, Dividing the historical data of heats within the historical time period into a preset number of second-level sets based on the preset number of second-level branches specifically includes: Performing clustering on the historical data of heats using the KNN algorithm according to the charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, and LIBs detection results in the historical data of heats; wherein, K in the KNN algorithm = the preset number of second-level branches; Obtaining a preset number of clustering sets and determining the clustering sets as second-level sets.

5. A top-bottom combined blown converter smelting monitoring system, characterized in that, The system includes: An acquisition module for obtaining the historical data of heats within a historical time period; wherein, the historical data of heats at least includes: charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, LIBs detection results, converter bottom blowing operation information, oxygen lance control position, charging situation; A partitioning module, configured to partition the heat history data within a historical time period into a preset number of secondary sets based on the preset number of secondary branches; An obtaining module, configured to use the secondary sets as training data to train a preset artificial intelligence algorithm to obtain trained models corresponding to the respective secondary sets; and further configured to obtain current heat detection data based on a preset acquisition time point, where the heat detection data at least includes: charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, LIBs detection results; determine a second set corresponding to the current heat detection data; and then input the current heat detection data into the trained model corresponding to the second set to obtain current converter bottom blowing operation information, oxygen lance control position, and charging conditions.

6. The top-bottom combined blown converter smelting monitoring system according to claim 5, characterized in that, The system further includes a collection module, configured to perform real-time detection of the oxygen lance gravity through a force sensor installed on the steel wire rope or rope pulley suspending the oxygen lance, and further obtain oxygen lance gravity data; Obtain a converter furnace mouth flame image, and identify the furnace mouth flame information corresponding to the converter furnace mouth flame image through an image recognition model; where the furnace mouth flame information at least includes: flame color, brightness, and texture.

7. The top-bottom combined blown converter smelting monitoring system according to claim 5, characterized in that, The partitioning module includes a first partitioning unit, configured to perform clustering of the heat history data using the KNN algorithm based on the charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, and LIBs detection results in the heat history data; where K in the KNN algorithm is equal to the preset number of secondary branches; Obtain a preset number of clustering sets, and determine the clustering sets as secondary sets.

8. The top-bottom combined blown converter smelting monitoring system according to claim 5, characterized in that, The obtaining module includes a second partitioning unit, configured to extract 10 pieces of heat history data from each second set as standard data; Use the charging conditions, flue gas data, audio data, oxygen lance gravity data, furnace mouth flame information, slag height, sublance measurement results, and LIBs detection results in the heat history data in the standard data as input data; Input the input data and the current heat detection data into the KNN algorithm to obtain the name of the second set of the input data in the clustering where the current heat detection data is located; Determine the name of the second set with the most occurrences as the second set corresponding to the current heat detection data.

9. A top-bottom combined blown converter smelting monitoring device, characterized in that, The device includes: A processor; And a memory, on which executable code is stored, and when the executable code is executed, the processor executes a top-bottom combined blowing converter smelting monitoring method according to any one of claims 1-4.

10. A non-volatile computer storage medium, characterized in that, Computer instructions are stored thereon, and when the computer instructions are executed, a top-bottom combined blowing converter smelting monitoring method according to any one of claims 1-4 is implemented.

Images