Steel ladle opening slag thickness control method and device, electronic equipment and storage medium

Through the combination of slag thickness sensor and prediction model, precise control of slag thickness on the ladle is achieved, solving the problem of difficult to achieve precise control by manual monitoring, and improving steel quality and equipment durability.

CN119076899APending Publication Date: 2024-12-06SGIS SONGSHAN CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411181853.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

Due to the limitations of manual monitoring, it is difficult to achieve precise control, resulting in unstable slag thickness, which may cause damage to the ladle or fluctuations in product quality, increasing production costs and safety hazards.

Method used

Data is collected through the slag thickness sensor, and the slag thickness range prediction model is input to determine whether the current slag thickness is within the safe range. If it is below the lower limit, add slag material. If it is above the upper limit, clean the slag material to ensure that the slag thickness is within a reasonable range. Recurrent neural networks are used to train the model to improve prediction accuracy.

Benefits of technology

It realizes precise control of ladle thickness, improves the quality and production efficiency of steel, extends the service life of the equipment, and reduces production costs and safety risks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119076899A_ABST
    Figure CN119076899A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides a steel ladle opening slag thickness control method and device, electronic equipment and a storage medium, and relates to the technical field of steelmaking. The current slag thickness of a steel ladle opening collected by a slag thickness sensor at the current moment and the slag thickness data of the steel ladle opening within the previous preset duration at the current moment are obtained, the slag thickness data are input into a slag thickness range prediction model, the slag thickness safety range corresponding to the slag thickness data is obtained, whether the current slag thickness is within the slag thickness safety range or not is judged, and the judgment result is judged. If the current slag thickness is smaller than the lower limit of the slag thickness safety range, a slag charge adding device is controlled to add slag charge into the steel ladle, and if the current slag thickness is larger than the upper limit of the slag thickness safety range, a slag charge cleaning device is controlled to remove slag charge from a steel ladle opening. Therefore, the slag thickness of the steel ladle opening can be accurately controlled, the slag thickness of the steel ladle opening is always good, and then the steel quality, the production efficiency and the durability of equipment are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of steelmaking, and in particular to a ladle mouth slag thickness control method, device, electronic equipment and storage medium. Background Art

[0002] The slag thickness at the ladle mouth is the first line of contact between molten steel and the external environment, and its state directly affects the quality of steel, production efficiency and equipment durability. If the slag thickness is too thin, the ladle will weaken the protection of the high-temperature molten steel, which may cause molten steel leakage, affect product quality and increase scrap rate; on the contrary, if the slag thickness is too thick, it will not only hinder the heat exchange of molten steel and affect the uniformity of composition, but also may cause overheating and burning of the inner wall of the ladle, shorten the service life of the ladle and increase maintenance costs.

[0003] At present, due to the limitations of manual monitoring, it is difficult to achieve precise control of slag thickness at the ladle mouth, resulting in unstable slag thickness, which may cause damage to the ladle or fluctuations in product quality. Over-reliance on manual operation is not only inefficient, but also prone to human errors, increasing production costs and safety hazards. Summary of the invention

[0004] In view of this, an object of the embodiments of the present invention is to provide a method, device, electronic device and storage medium for controlling slag thickness at a ladle mouth to at least partially improve the above-mentioned problem.

[0005] In order to achieve the above purpose, the technical solution adopted by the embodiment of the present invention is as follows:

[0006] In a first aspect, an embodiment of the present invention provides a method for controlling slag thickness at a ladle mouth, which is applied to a controller, wherein the controller is respectively connected to a slag thickness sensor, a slag adding device, and a slag cleaning device for communication, and the method comprises:

[0007] Acquire the current slag thickness at the ladle opening collected by the slag thickness sensor at the current moment and the slag thickness data at the ladle opening within a preset time period before the current moment;

[0008] Inputting the slag thickness data into a slag thickness range prediction model to obtain a slag thickness safety range corresponding to the slag thickness data;

[0009] Determining whether the current slag thickness is within the slag thickness safety range;

[0010] If the current slag thickness is less than the lower limit of the slag thickness safety range, controlling the slag adding device to add slag to the ladle;

[0011] If the current slag thickness is greater than the upper limit of the slag thickness safety range, the slag cleaning device is controlled to remove slag from the ladle mouth.

[0012] Optionally, the step of inputting the slag thickness data into a slag thickness range prediction model to obtain a slag thickness safety range corresponding to the slag thickness data includes:

[0013] Extracting features from the slag thickness data to obtain time domain features and frequency domain features;

[0014] A slag thickness safety range corresponding to the slag thickness data is determined according to the time domain characteristics and the frequency domain characteristics.

[0015] Optionally, controlling the slag adding device to add slag to the ladle comprises:

[0016] Acquire the geometric dimensions of the ladle, and calculate the mass of the required slag according to the geometric dimensions, the current slag thickness, and the slag thickness safety range;

[0017] Calculating the feeding speed of the added slag according to the mass of the required slag and the preset feeding rules;

[0018] Slag is added to the ladle at the feeding rate.

[0019] Optionally, the calculating the mass of the required slag material according to the geometric size, the current slag thickness and the slag thickness safety range includes:

[0020] The middle value of the slag thickness safety range is selected as the target slag thickness, and the required slag volume is calculated according to the target slag thickness and the current slag thickness; wherein the formula for calculating the required slag volume is as follows:

[0021] ΔV=πr 2 (h t -h c )

[0022] Wherein, ΔV is the volume of the required slag, π is the pi, r is the radius of the ladle, h t is the target slag thickness, h c is the current slag thickness;

[0023] The bulk density of the slag is obtained, and the mass of the required slag is calculated according to the bulk density and the volume of the required slag; wherein the formula for calculating the mass of the required slag is as follows:

[0024] m=ΔV×ρ

[0025] Wherein, ρ is the bulk density of the slag, and ΔV is the volume of the required slag.

[0026] Optionally, the method further comprises:

[0027] At a preset time point, a standard metal sheet with known true thickness is placed within the measuring range of the slag thickness sensor;

[0028] Obtaining the measured thickness of the standard metal sheet collected by the slag thickness sensor;

[0029] Calculating a deviation between the measured thickness and the true thickness;

[0030] When the deviation value exceeds a preset range, the calibration parameters of the slag thickness sensor are adjusted according to the deviation value until the measured thickness is consistent with the true thickness or the deviation value is within the preset range.

[0031] Optionally, the method further comprises a step of training a slag thickness range prediction model, the training step comprising:

[0032] Acquire historical slag thickness data collected by a slag thickness sensor; the historical slag thickness sensor collects data at a preset period;

[0033] Preprocessing the historical slag thickness data to obtain a plurality of slag thickness window data; the slag thickness window data includes a plurality of the historical slag thickness data;

[0034] Performing feature extraction on each of the slag thickness window data to obtain slag thickness feature data of each of the slag thickness window data, and marking a true slag thickness safety range on each of the slag thickness window data;

[0035] The slag thickness characteristic data and the actual slag thickness safety range are input into the slag thickness range prediction model for training to obtain a mature slag thickness range prediction model.

[0036] Optionally, the slag thickness range prediction model uses a recurrent neural network, and the slag thickness feature data is input into the slag thickness range prediction model for training to obtain a mature slag thickness range prediction model, including:

[0037] Taking a batch of the slag thickness characteristic data sets, and for any of the slag thickness characteristic data, calculating a predicted slag thickness safety range corresponding to the slag thickness characteristic data;

[0038] The loss information of the predicted slag thickness safety range and the actual slag thickness safety range corresponding to the slag thickness characteristic data is calculated using a mean square error loss function; the loss information represents the difference between the predicted slag thickness safety range and the actual slag thickness safety range of the slag thickness range prediction model in the current training cycle;

[0039] The parameters of the slag thickness range prediction model are updated according to the loss information until the loss information corresponding to the Nth training cycle meets the preset conditions, and the slag thickness range prediction model corresponding to the Nth training cycle is used as a mature slag thickness range prediction model.

[0040] In a second aspect, an embodiment of the present invention provides a ladle mouth slag thickness control device, which is applied to a controller, wherein the controller is respectively connected to a slag thickness sensor, a slag adding device, and a slag cleaning device for communication, and the device comprises:

[0041] A data acquisition unit, used to acquire the current slag thickness of the ladle mouth collected by the slag thickness sensor at the current moment and the slag thickness data of the ladle mouth within a preset time period before the current moment;

[0042] A slag thickness safety range acquisition unit, used for inputting the slag thickness data into a slag thickness range prediction model to obtain a slag thickness safety range corresponding to the slag thickness data;

[0043] A slag thickness judging unit, used for judging whether the current slag thickness is within the slag thickness safety range;

[0044] A slag adding unit, configured to control the slag adding device to add slag to the ladle if the current slag thickness is less than the lower limit of the slag thickness safety range;

[0045] The slag removing unit is used to control the slag cleaning device to remove slag from the ladle mouth if the current slag thickness is greater than the upper limit of the slag thickness safety range.

[0046] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above-described methods when executing the program.

[0047] In a fourth aspect, an embodiment of the present invention provides a storage medium having a computer program stored thereon, wherein the computer program implements any of the above-described methods when executed by a processor.

[0048] The embodiments of the present invention provide a method, device, electronic device and storage medium for controlling the slag thickness at the ladle mouth. The method obtains the current slag thickness of the ladle mouth collected by the slag thickness sensor at the current moment and the slag thickness data of the ladle mouth within a preset time period before the current moment, processes and calculates the slag thickness data, and then processes the slag thickness at the ladle mouth to ensure that the slag thickness at the ladle mouth is always at an optimal thickness, thereby being able to accurately control the slag thickness at the ladle mouth, thereby improving the quality of steel, production efficiency and durability of equipment.

[0049] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0051] Figure 1 A schematic structural block diagram of an electronic device provided by an embodiment of the present invention;

[0052] Figure 2 A schematic flow chart of a method for controlling slag thickness at a ladle mouth provided in an embodiment of the present invention;

[0053] Figure 3 Another schematic diagram of a flow chart of a ladle mouth slag thickness control method provided by an embodiment of the present invention;

[0054] Figure 4 A schematic diagram of a flow chart of a slag thickness range prediction model training step provided by an embodiment of the present invention;

[0055] Figure 5 A schematic structural block diagram of a ladle mouth slag thickness control device provided in an embodiment of the present invention.

[0056] Icons: 100-electronic device; 101-memory; 102-communication interface; 103-processor; 104-bus; 300-ladle mouth slag thickness control device; 310-data acquisition unit; 320-slag thickness safety range acquisition unit; 330-slag thickness judgment unit; 340-slag adding unit; 350-slag removing unit. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0058] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. 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.

[0059] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0060] 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 any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0061] The slag thickness at the ladle mouth is the first line of contact between molten steel and the external environment, and its state directly affects the quality of steel, production efficiency and equipment durability. If the slag thickness is too thin, the ladle will weaken the protection of the high-temperature molten steel, which may cause molten steel leakage, affect product quality and increase scrap rate; on the contrary, if the slag thickness is too thick, it will not only hinder the heat exchange of molten steel and affect the uniformity of composition, but also may cause overheating and burning of the inner wall of the ladle, shorten the service life of the ladle and increase maintenance costs.

[0062] In current steel production, the management of slag thickness at the ladle mouth faces a series of problems and challenges. First, due to the limitations of manual monitoring, it is difficult to achieve real-time and accurate control of slag thickness, resulting in unstable slag thickness, which may cause damage to the ladle or fluctuations in product quality. Secondly, over-reliance on manual operation is not only inefficient, but also prone to human errors, increasing production costs and safety hazards. In addition, the traditional slag thickness adjustment method lacks continuity and predictability, and cannot be dynamically adjusted according to the flow characteristics of molten steel, which limits the service life of the ladle.

[0063] At present, traditional ladle management mainly relies on manual monitoring and regular maintenance, which has problems such as low work efficiency, low slag thickness control accuracy and irregular maintenance cycle. Due to the limitations of manual monitoring, it is difficult to achieve precise control of slag thickness at the ladle mouth, resulting in unstable slag thickness, which may cause damage to the ladle or fluctuations in product quality. Excessive reliance on manual operation is not only inefficient, but also prone to human errors, increasing production costs and safety hazards.

[0064] Based on the above situation, an embodiment of the present invention provides a method, device, electronic device and storage medium for controlling the slag thickness at the ladle mouth. The slag thickness data at the ladle mouth is collected by a slag thickness sensor, and the current reasonable thickness of the slag at the ladle mouth is calculated. The slag thickness at the ladle mouth is then processed, so that the slag thickness at the ladle mouth can be accurately controlled, so that the slag thickness at the ladle mouth is always at an optimal thickness, thereby improving the quality of steel, production efficiency and durability of equipment.

[0065] To implement the process steps and functions of each example of the present invention, please refer to Figure 1 , Figure 1 A schematic structural block diagram of an electronic device provided by an embodiment of the present invention. The electronic device 100 includes a memory 101 and a processor 103, and the memory 101 and the processor 103 are electrically connected to each other directly or indirectly to realize data transmission or interaction. For example, these elements can be electrically connected to each other through one or more communication buses 104 or signal lines. The memory 101 can be used to store software programs and modules, and the processor 103 executes the software programs and modules stored in the memory 101 to perform various functional applications and data processing.

[0066] The electronic device 100 may be, but is not limited to, a personal computer (PC), a server, a distributed computer, etc. It is understandable that the electronic device 100 is not limited to a physical server, but may also be a virtual machine on a physical server, a virtual machine built on a cloud platform, etc., which can provide the same functions as the server or virtual machine. The operating system of the electronic device 100 may be, but is not limited to, a Windows system, a Linux system, etc.

[0067] Among them, the memory 101 can be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), etc.

[0068] The communication connection between the electronic device 100 and an external device is achieved through at least one communication interface 102 (which can be wired or wireless).

[0069] The processor 103 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the embodiment of the present invention can be completed by the hardware integrated logic circuit in the processor 103 or the instructions in the form of software. The processor 103 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0070] Understandably, Figure 1 The structure shown is for illustration only. The electronic device 100 may also include Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown. Figure 1 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0071] The following is an exemplary description of the ladle mouth slag thickness control method provided by the present invention. Specifically, Figure 2 A schematic diagram of a ladle mouth slag thickness control method provided by an embodiment of the present invention, see Figure 2 The method is applied to a controller, which is respectively connected to the slag thickness sensor, the slag adding device and the slag cleaning device in communication. The controller can be the above Figure 1 The electronic device 100 shown in FIG. 1 includes: Figure 2 The following steps are described:

[0072] S210: Acquire the current slag thickness at the ladle opening collected by the slag thickness sensor at the current moment and the slag thickness data at the ladle opening within a preset time period before the current moment.

[0073] Slag thickness sensors can be high-temperature slag thickness measuring instruments that can capture the thickness changes of the slag layer at the ladle mouth in real time and accurately. These sensors are installed at key locations at the ladle mouth, can withstand extreme high temperature environments and transmit data stably, and the slag thickness sensors are non-contact installed to prevent impact on the ladle working environment.

[0074] The slag thickness sensor continuously measures the thickness of the slag layer at the ladle mouth, generates a series of continuous numerical data points, controls the acquisition of the slag thickness at the ladle mouth at the current moment, and simultaneously obtains the slag thickness data of the ladle mouth within the previous preset time period. The preset time period can be in minutes or hours. In more sophisticated steelmaking operations, the minute level can be used, such as a preset time of 10 minutes. In larger steelmaking operations, the hour level can be used, such as a preset time of 1 hour.

[0075] S220: Inputting the slag thickness data into a slag thickness range prediction model to obtain a slag thickness safety range corresponding to the slag thickness data.

[0076] The slag thickness range prediction model is a trained model that can predict the safe range of the slag thickness at the ladle mouth within a period of time based on the slag thickness data at the ladle mouth within the period of time.

[0077] In another possible implementation, a slag thickness safety range is preset directly in the control, for example, 10mm to 20mm, and the slag thickness at the ladle mouth at any time is compared with the slag thickness safety range. This method is not as detailed in controlling the slag thickness at the ladle mouth, but it is simpler and more efficient.

[0078] S230: Determine whether the current slag thickness is within a safe range of slag thickness.

[0079] S240: If the current slag thickness is less than the lower limit of the slag thickness safety range, control the slag adding device to add slag to the ladle.

[0080] If the slag thickness at the ladle mouth is too thin, it will weaken the protection of the ladle for high-temperature molten steel, which may cause molten steel leakage, affect product quality and increase scrap rate. Therefore, when the current slag thickness is less than the lower limit of the slag thickness safety range, it is necessary to add slag to the ladle by controlling the slag adding device to increase the slag thickness at the ladle mouth to within the safety range. Doing so can avoid potential problems caused by the slag thickness at the ladle mouth being too thin and ensure the continuity and stability of the steelmaking process.

[0081] S250: If the current slag thickness is greater than the upper limit of the slag thickness safety range, the slag cleaning device is controlled to remove slag from the ladle mouth.

[0082] Too much slag at the ladle mouth will not only hinder the heat exchange of molten steel and affect the uniformity of composition, but may also cause overheating and burning of the inner wall of the ladle, shorten the service life of the ladle, and increase maintenance costs. Therefore, when the current slag thickness is greater than the upper limit of the slag thickness safety range, the slag can be removed from the ladle mouth by controlling the slag cleaning device to keep the slag thickness at the ladle mouth within the safety range.

[0083] The method obtains the current slag thickness of the ladle mouth collected by the slag thickness sensor at the current moment and the slag thickness data of the ladle mouth within a preset time period before the current moment, and after processing and calculating the slag thickness data, obtains the safety range that the current slag thickness at the ladle mouth should be in, and then processes the slag thickness at the ladle mouth to keep the slag thickness at the ladle mouth at an optimal thickness, thereby being able to accurately control the slag thickness at the ladle mouth, thereby improving steel quality, production efficiency and equipment durability.

[0084] Furthermore, in order to make the slag thickness safety range calculated by the slag thickness range prediction model more accurate, multi-dimensional feature extraction may be performed on the slag thickness data, such as time domain features and frequency domain features. Specifically, the above step S220 may include the following steps:

[0085] S221: Extract features from the slag thickness data to obtain time domain features and frequency domain features.

[0086] The slag thickness data are multiple slag thickness values ​​within a period of time. The key features in the data can be identified through mathematical statistics and signal processing technology to obtain features in both time domain and frequency domain.

[0087] Among them, time domain features may include: mean, median, mode, standard deviation, variance, maximum value, minimum value, moving average, etc.; frequency domain features can be obtained using Fourier transform.

[0088] S222: Determine a slag thickness safety range corresponding to the slag thickness data according to the time domain characteristics and the frequency domain characteristics.

[0089] According to the obtained time domain characteristics and frequency domain characteristics, the slag thickness safety range at the ladle mouth within the period of time can be obtained through the slag thickness range prediction model.

[0090] The method of obtaining the slag thickness safety range can adapt to different steelmaking scenarios and scenarios in different time periods. According to different scenarios, a more appropriate slag thickness safety range can be obtained, and the slag thickness at the ladle mouth can be better controlled.

[0091] When it is determined that the current slag thickness is less than the lower limit of the slag thickness safety range, there are many ways to add slag to the ladle, such as directly adding slag to the ladle. However, in order to better control the addition of slag, the mass of slag to be added can be calculated, and then slag can be added according to the mass. Optionally, see Figure 3 , Figure 3 Another schematic flow chart of a ladle mouth slag thickness control method provided by an embodiment of the present invention, the step of controlling the slag adding device to add slag to the ladle may include: Figure 3 The following steps are shown:

[0092] S241: Obtain the geometric dimensions of the ladle, and calculate the mass of the required slag based on the geometric dimensions, the current slag thickness, and the safety range of the slag thickness.

[0093] The geometric dimensions, current slag thickness and slag thickness safety range can be used to calculate the mass of the required slag using a mathematical formula, wherein a value within the slag thickness safety range needs to be taken as the target slag thickness. Specifically, the steps of calculating the mass of the required slag may include:

[0094] The middle value of the slag thickness safety range is selected as the target slag thickness, and the required slag volume is calculated based on the target slag thickness and the current slag thickness; the formula for calculating the required slag volume is as follows:

[0095] ΔV=πr 2 (h t -h c )

[0096] Wherein, ΔV is the volume of the required slag, π is the pi, r is the radius of the ladle, h t is the target slag thickness, h c is the current slag thickness.

[0097] The bulk density of the slag is obtained, and the mass of the required slag is calculated according to the bulk density and the volume of the required slag; wherein the formula for calculating the mass of the required slag is as follows:

[0098] m=ΔV×ρ

[0099] Among them, ρ is the bulk density of the slag, and ΔV is the volume of the required slag.

[0100] S242: Calculate the feeding speed of the added slag according to the required slag mass and the preset feeding rules.

[0101] The feeding rule can be constant or progressive. If it is a constant method, the feeding rate is obtained by dividing the mass of the required slag by the planned feeding time. If it is a progressive method, the feeding rate can be faster in the initial stage and then gradually reduced over a certain period of time.

[0102] S243: adding slag to the ladle at a feeding speed.

[0103] Slag is added to the ladle according to the calculated feeding speed until the slag thickness at the ladle mouth reaches the target slag thickness.

[0104] After the system has been running for a period of time, the measurement accuracy of the slag thickness sensor may decrease. In order to make the slag thickness of the ladle mouth slag thickness control method more accurate, the method can also calibrate the slag thickness sensor regularly. The method can also include:

[0105] At a preset time point, a standard metal sheet with known true thickness is placed within the measuring range of the slag thickness sensor.

[0106] Get the measured thickness of the standard metal sheet collected by the slag thickness sensor.

[0107] Calculate the deviation between the measured thickness and the true thickness.

[0108] When the deviation value exceeds the preset range, the calibration parameters of the slag thickness sensor are adjusted according to the deviation value until the measured thickness is consistent with the actual thickness or the deviation value is within the preset range.

[0109] In actual operation, the robot arm can be controlled regularly to place the standard metal sheet at a specific position of the ladle mouth. This position should be within the measurement range of the sensor, and the thickness of the standard metal sheet is known. Turn on the sensor, record the measured thickness of the standard metal sheet currently displayed, compare the sensor reading with the actual thickness, and calculate the deviation. If the deviation exceeds the preset range, the calibration parameters of the sensor need to be adjusted.

[0110] In a possible implementation, the method may further include a step of training a slag thickness range prediction model. For details, see Figure 4 , Figure 4 A schematic flow chart of a slag thickness range prediction model training step provided in an embodiment of the present invention, wherein the training step may include: Figure 4 The following steps are shown:

[0111] S410: Acquire historical slag thickness data collected by the slag thickness sensor.

[0112] The slag thickness sensor collects data at a preset period, which may be once every second.

[0113] S420: Preprocess the historical slag thickness data to obtain a plurality of slag thickness window data.

[0114] The data contained in each slag thickness window data is consistent with the data volume of the slag thickness data at the ladle mouth within the preset time period in step S210, for example, all of which are data within one hour.

[0115] S430: extracting features from the data of each slag thickness window to obtain slag thickness feature data of each slag thickness window data, and marking a true slag thickness safety range for each slag thickness window data.

[0116] The data of each window is processed in the same manner as in step S221 to obtain the time domain characteristics and frequency domain characteristics of each slag thickness window data, and the real slag thickness safety range is marked for each slag thickness window data for subsequent training.

[0117] S440: Inputting each slag thickness characteristic data and each actual slag thickness safety range into a slag thickness range prediction model for training, thereby obtaining a mature slag thickness range prediction model.

[0118] Specifically, the slag thickness range prediction model can be initialized using a recurrent neural network, and the training process may include the following steps:

[0119] S441: taking a batch of slag thickness characteristic data sets, and for any slag thickness characteristic data, calculating a predicted slag thickness safety range corresponding to the slag thickness characteristic data.

[0120] S442: using a mean square error loss function to calculate loss information of the predicted slag thickness safety range and the actual slag thickness safety range corresponding to the slag thickness characteristic data; wherein the loss information represents the difference between the predicted slag thickness safety range of the slag thickness range prediction model in the current training cycle and the actual slag thickness safety range.

[0121] S443: updating the parameters of the slag thickness range prediction model according to the loss information until the loss information corresponding to the Nth training cycle meets the preset conditions, and then taking the slag thickness range prediction model corresponding to the Nth training cycle as the mature slag thickness range prediction model.

[0122] Take a batch of slag thickness feature data sets, for example, 100 slag thickness feature data, and input any slag thickness feature data into the slag thickness range prediction model, then the predicted slag thickness safety range corresponding to the slag thickness window data can be obtained, and then the mean square error loss function is used to calculate the loss information of the 100 predicted slag thickness safety ranges and the actual slag thickness safety ranges corresponding to the 100 slag thickness feature data, and the parameters of the slag thickness range prediction model are updated according to the loss information to complete a training cycle. That is, 100 slag thickness window data correspond to one training cycle. Among them, the mean square error loss function is:

[0123]

[0124] Where N is the number of slag thickness characteristic data in a batch, Y i is the i-th real slag thickness safety range, is the i-th predicted slag thickness safety range.

[0125] Furthermore, the embodiment of the present invention also provides a ladle mouth slag thickness control device 300, see Figure 5 , Figure 5 The present invention provides a schematic structural block diagram of a ladle mouth slag thickness control device. The ladle mouth slag thickness control device 300 is applied to a controller. The controller is respectively connected to a slag thickness sensor, a slag adding device, and a slag cleaning device. The ladle mouth slag thickness control device 300 includes:

[0126] The data acquisition unit 310 is used to acquire the current slag thickness at the ladle opening collected by the slag thickness sensor at the current moment and the slag thickness data at the ladle opening within a preset time period before the current moment.

[0127] The slag thickness safety range acquisition unit 320 is used to input the slag thickness data into the slag thickness range prediction model to obtain the slag thickness safety range corresponding to the slag thickness data.

[0128] The slag thickness judging unit 330 is used to judge whether the current slag thickness is within the slag thickness safety range.

[0129] The slag adding unit 340 is used to control the slag adding device to add slag to the ladle if the current slag thickness is less than the lower limit of the slag thickness safety range.

[0130] The slag removing unit 350 is used to control the slag cleaning device to remove slag from the ladle mouth if the current slag thickness is greater than the upper limit of the slag thickness safety range.

[0131] In summary, the embodiment of the present invention provides a method, device, electronic device and storage medium for controlling the slag thickness at the ladle mouth, which can obtain the current slag thickness and the safety range of the current slag thickness at the ladle mouth through the data collected by the slag thickness sensor. When the monitored slag thickness is lower than the lower limit, the control system will start the slag adding device, and gradually increase the slag thickness in a constant or gradual manner by accurately calculating the required amount of slag to ensure that it is stable within the set range. On the contrary, if the slag thickness exceeds the upper limit, the control system will start the cleaning device, and reduce the slag thickness at the ladle mouth by controlling the slag cleaning speed, so as to maintain the balance of the slag layer thickness. Thereby, the quality of steel, production efficiency and durability of equipment can be improved.

[0132] By implementing this method, the ladle service life, slag thickness stability and production cost before and after the traditional manual control and automatic repair of ladle mouth slag thickness were compared. The results showed that the automatic repair method significantly improved the average service life of the ladle, with an average increase of more than 20%, and reduced the number of production interruptions caused by slag thickness problems. At the same time, through precise slag control, the slag thickness fluctuation range is significantly reduced, ensuring the quality of molten steel and heat conduction efficiency. In terms of economic benefits, although additional equipment installation and system integration costs may be required in the early stage, in the long run, due to the reduction of manual intervention and slag waste, the overall production cost is saved by about 15%. In addition, the reduced fault repair costs and improved product quality have improved the overall return on investment.

[0133] Compared with traditional manual adjustment, this method significantly reduces the average slag thickness deviation, reduces the incidence of ladle leakage by 30%, and increases the service life of the ladle from an average of 60 furnaces to more than 80 furnaces. In addition, due to precise slag control, the slag consumption in the production process is reduced by 15%, directly saving about 20% of production costs.

[0134] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and a module, a program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0135] In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0136] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a computer-readable storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0137] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0138] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A method for controlling slag thickness at ladle mouth, characterized in that: Applied to a controller, the controller is respectively connected to a slag thickness sensor, a slag adding device, and a slag cleaning device for communication, the method comprising: Acquire the current slag thickness at the ladle opening collected by the slag thickness sensor at the current moment and the slag thickness data at the ladle opening within a preset time period before the current moment; Inputting the slag thickness data into a slag thickness range prediction model to obtain a slag thickness safety range corresponding to the slag thickness data; Determining whether the current slag thickness is within the slag thickness safety range; If the current slag thickness is less than the lower limit of the slag thickness safety range, controlling the slag adding device to add slag to the ladle; If the current slag thickness is greater than the upper limit of the slag thickness safety range, the slag cleaning device is controlled to remove slag from the ladle mouth.

2. The method according to claim 1, characterized in that The step of inputting the slag thickness data into a slag thickness range prediction model to obtain a slag thickness safety range corresponding to the slag thickness data includes: Extracting features from the slag thickness data to obtain time domain features and frequency domain features; A slag thickness safety range corresponding to the slag thickness data is determined according to the time domain characteristics and the frequency domain characteristics.

3. The method according to claim 1, characterized in that The controlling the slag adding device to add slag to the ladle comprises: Acquire the geometric dimensions of the ladle, and calculate the mass of the required slag according to the geometric dimensions, the current slag thickness, and the slag thickness safety range; Calculating the feeding speed of the added slag according to the mass of the required slag and the preset feeding rules; Slag is added to the ladle at the feeding rate.

4. The method according to claim 3, characterized in that The step of calculating the mass of the required slag material according to the geometric dimensions, the current slag thickness and the slag thickness safety range includes: The middle value of the slag thickness safety range is selected as the target slag thickness, and the required slag volume is calculated according to the target slag thickness and the current slag thickness; wherein the formula for calculating the required slag volume is as follows: ΔV=πr 2 (h t -h c ) Wherein, ΔV is the volume of the required slag, π is the pi, r is the radius of the ladle, h t is the target slag thickness, h c is the current slag thickness; The bulk density of the slag is obtained, and the mass of the required slag is calculated according to the bulk density and the volume of the required slag; wherein the formula for calculating the mass of the required slag is as follows: m=ΔV×ρ Wherein, ρ is the bulk density of the slag, and ΔV is the volume of the required slag.

5. The method according to claim 1, characterized in that The method further comprises: At a preset time point, a standard metal sheet with known true thickness is placed within the measuring range of the slag thickness sensor; Obtaining the measured thickness of the standard metal sheet collected by the slag thickness sensor; Calculating a deviation between the measured thickness and the true thickness; When the deviation value exceeds a preset range, the calibration parameters of the slag thickness sensor are adjusted according to the deviation value until the measured thickness is consistent with the true thickness or the deviation value is within the preset range.

6. The method according to claim 1, characterized in that The method further comprises a step of training a slag thickness range prediction model, wherein the training step comprises: Acquire historical slag thickness data collected by a slag thickness sensor; the historical slag thickness sensor collects data at a preset period; Preprocessing the historical slag thickness data to obtain a plurality of slag thickness window data; the slag thickness window data includes a plurality of the historical slag thickness data; Performing feature extraction on each of the slag thickness window data to obtain slag thickness feature data of each of the slag thickness window data, and marking a true slag thickness safety range on each of the slag thickness window data; The slag thickness characteristic data and the actual slag thickness safety range are input into the slag thickness range prediction model for training to obtain a mature slag thickness range prediction model.

7. The method according to claim 1, characterized in that The slag thickness range prediction model uses a recurrent neural network, and the slag thickness feature data is input into the slag thickness range prediction model for training to obtain a mature slag thickness range prediction model, including: Taking a batch of the slag thickness characteristic data sets, and for any of the slag thickness characteristic data, calculating a predicted slag thickness safety range corresponding to the slag thickness characteristic data; The loss information of the predicted slag thickness safety range and the actual slag thickness safety range corresponding to the slag thickness characteristic data is calculated using a mean square error loss function; the loss information represents the difference between the predicted slag thickness safety range and the actual slag thickness safety range of the slag thickness range prediction model in the current training cycle; The parameters of the slag thickness range prediction model are updated according to the loss information until the loss information corresponding to the Nth training cycle meets the preset conditions, and the slag thickness range prediction model corresponding to the Nth training cycle is used as a mature slag thickness range prediction model.

8. A ladle mouth slag thickness control device, characterized in that: Applied to a controller, the controller is respectively connected to a slag thickness sensor, a slag adding device and a slag cleaning device for communication, and the device comprises: A data acquisition unit, used to acquire the current slag thickness of the ladle mouth collected by the slag thickness sensor at the current moment and the slag thickness data of the ladle mouth within a preset time period before the current moment; A slag thickness safety range acquisition unit, used for inputting the slag thickness data into a slag thickness range prediction model to obtain a slag thickness safety range corresponding to the slag thickness data; A slag thickness judging unit, used for judging whether the current slag thickness is within the slag thickness safety range; A slag adding unit, configured to control the slag adding device to add slag to the ladle if the current slag thickness is less than the lower limit of the slag thickness safety range; The slag removing unit is used to control the slag cleaning device to remove slag from the ladle mouth if the current slag thickness is greater than the upper limit of the slag thickness safety range.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.