CN118072876A - Ladle slag skimming control method and device, electronic equipment and storage medium - Google Patents
Ladle slag skimming control method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN118072876A CN118072876A CN202410035215.0A CN202410035215A CN118072876A CN 118072876 A CN118072876 A CN 118072876A CN 202410035215 A CN202410035215 A CN 202410035215A CN 118072876 A CN118072876 A CN 118072876A
- Authority
- CN
- China
- Prior art keywords
- slag
- parameter
- skimming
- prediction
- raking
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 70
- 239000002893 slag Substances 0.000 title claims description 287
- 238000012549 training Methods 0.000 claims description 29
- 229910000831 Steel Inorganic materials 0.000 claims description 24
- 239000010959 steel Substances 0.000 claims description 24
- 238000012417 linear regression Methods 0.000 claims description 20
- 238000004891 communication Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 abstract description 30
- 238000004364 calculation method Methods 0.000 description 14
- 239000007788 liquid Substances 0.000 description 13
- 239000012535 impurity Substances 0.000 description 6
- 230000009471 action Effects 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 229910052751 metal Inorganic materials 0.000 description 4
- 239000002184 metal Substances 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000003723 Smelting Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 238000009628 steelmaking Methods 0.000 description 2
- 229910000838 Al alloy Inorganic materials 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000000155 melt Substances 0.000 description 1
- 238000010310 metallurgical process Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003756 stirring Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Continuous Casting (AREA)
Abstract
The application relates to a ladle slag-off control method, a device, electronic equipment and a storage medium, wherein the ladle slag-off control method is used for obtaining ladle slag-off input data, respectively carrying out linear prediction and nonlinear prediction based on the slag-off input data to obtain linear slag-off prediction data and nonlinear slag-off prediction data, and determining target prediction data corresponding to the slag-off input data by adopting the linear slag-off prediction data and the nonlinear slag-off prediction data, so that slag-off control can be carried out on the ladle according to the target prediction data, the slag-off data do not need to be determined manually in the slag-off process, and the slag-off accuracy and efficiency are improved.
Description
Technical Field
The present application relates to the field of automation control, and in particular, to a method and apparatus for controlling slag skimming of a ladle, an electronic device, and a storage medium.
Background
Slag skimming is a key step in metallurgical processes, and aims to remove or clean oxides, impurities, undesirable metal inclusions and the like on the surface of molten metal through a physical or chemical method, so that the quality and purity of steel are improved. The process is widely applied to a plurality of metallurgical links such as steelmaking, aluminum alloy smelting and the like.
Especially in the steelmaking process, slag skimming is an indispensable link. In actual operation, when the furnace burden is fully melted in the smelting furnace and the temperature of the melt reaches the smelting temperature, stirring and slag skimming operations can be started. When the slag is removed, the slag removal operation is started after the ladle containing molten steel is tilted by a certain angle so that the liquid level and the edge of the ladle are basically leveled, and when the slag is removed, the slag removal operation is required to be performed according to different slag removal data, such as tilting angle, slag removal duration or slag removal times; in the prior art, the determination of the slag skimming data is mainly performed by manual judgment and determination, namely, slag skimming operation is performed by setting the slag skimming data according to operation experience by an operator. However, the manual determination of the slag-off data depends on experience and judgment of operators, and the condition that each ladle needs to be watched manually in the slag-off process takes time, so that the efficiency is affected, the accuracy of slag-off control is reduced due to the subjective influence of the operators.
Disclosure of Invention
In order to solve the technical problems, the application provides a ladle slag skimming control method, a ladle slag skimming control device, electronic equipment and a storage medium.
In a first aspect, the present application provides a method for controlling slag skimming of a ladle, including:
Acquiring slag skimming input data of a ladle;
Based on the slagging-off input data, respectively performing linear prediction and nonlinear prediction to obtain linear slagging-off prediction data and nonlinear slagging-off prediction data;
Determining target prediction data corresponding to the slag-raking input data by adopting the linear slag-raking prediction data and the nonlinear slag-raking prediction data;
and carrying out slag skimming control on the steel ladle according to the target prediction data.
Optionally, performing linear prediction based on the slagging-off input data to obtain linear slagging-off prediction data, including:
Acquiring a preset linear regression parameter;
performing linear prediction by adopting the linear regression parameters and the slag-raking input data to obtain a first slag-raking start angle parameter, a first slag-raking end angle parameter, a first slag-raking duration parameter and a first slag-raking frequency parameter;
And determining the first slag skimming start angle parameter, the first slag skimming end angle parameter, the first slag skimming duration parameter and the first slag skimming frequency parameter as the linear slag skimming prediction data.
Optionally, performing nonlinear prediction based on the slagging-off input data to obtain nonlinear slagging-off prediction data, including:
Inputting the slagging-off input data into a pre-trained nonlinear prediction model to predict, and obtaining an output result of the nonlinear prediction model;
Extracting a second slag skimming start angle parameter, a second slag skimming end angle parameter, a second slag skimming duration parameter and a second slag skimming frequency parameter from the output result;
and determining the second slag skimming start angle parameter, the second slag skimming end angle parameter, the second slag skimming duration parameter and the second slag skimming frequency parameter as the nonlinear slag skimming prediction data.
Optionally, the determining, using the linear slag-off prediction data and the nonlinear slag-off prediction data, the target prediction data corresponding to the slag-off input data includes:
Calculating by adopting the linear slag-off prediction data and the nonlinear slag-off prediction data to obtain a slag-off prediction data average value;
and determining the target prediction data based on the average value of the slag skimming prediction data.
Optionally, the performing slag removal control on the ladle according to the target prediction data includes:
Generating a control instruction of the slag removing device according to the target prediction data;
based on the control instruction, carrying out slag skimming treatment on the steel ladle through slag skimming equipment, and acquiring real-time slag skimming parameters of the slag skimming equipment;
And generating slag-raking ending information under the condition that the real-time slag-raking parameters meet the ending conditions corresponding to the target prediction parameters.
Optionally, the target prediction data includes a target slag-off end angle parameter, a target slag-off duration parameter, and a target slag-off frequency parameter, and the real-time slag-off parameters include a real-time slag-off angle parameter, a real-time slag-off duration parameter, and a real-time slag-off frequency parameter;
After the real-time slag skimming parameters of the slag skimming device are obtained, the method further comprises the following steps:
Determining that the real-time slag skimming parameter meets the ending condition corresponding to the target prediction parameter under the condition that the real-time slag skimming angle parameter reaches the target slag skimming ending angle parameter and the real-time slag skimming duration parameter reaches the target slag skimming duration parameter; or alternatively
Determining that the real-time slag skimming parameter meets the ending condition corresponding to the target prediction parameter under the condition that the real-time slag skimming angle parameter reaches the target slag skimming ending angle parameter and the real-time slag skimming frequency parameter reaches the target slag skimming frequency parameter; or alternatively
And determining that the real-time slag skimming parameter meets the ending condition corresponding to the target prediction parameter under the condition that the real-time slag skimming frequency parameter reaches the target slag skimming frequency parameter and the real-time slag skimming duration parameter reaches the target slag skimming duration parameter.
Optionally, after the slag skimming control is performed on the ladle according to the target prediction data, the method further includes:
acquiring slag-off ending parameters of the steel ladle based on the slag-off ending information;
Under the condition that the slag skimming end parameter meets the preset condition, updating a training sample set of a nonlinear prediction model by adopting the slag skimming end parameter and the slag skimming input data, and determining the updating quantity of the training sample set;
And under the condition that the update quantity reaches a preset update quantity threshold value, retraining the nonlinear prediction model by adopting sample data in the training sample set, wherein the sample data comprises the slagging-off ending parameter and the slagging-off input data.
In a second aspect, the present application provides a slag skimming control device for a ladle, comprising:
The acquisition module is used for acquiring the slagging-off input data of the ladle;
the prediction module is used for respectively carrying out linear prediction and nonlinear prediction based on the slag-raking input data to obtain linear slag-raking prediction data and nonlinear slag-raking prediction data;
The determining module is used for determining target prediction data corresponding to the slag-raking input data by adopting the linear slag-raking prediction data and the nonlinear slag-raking prediction data;
and the control module is used for carrying out slag skimming control on the steel ladle according to the target prediction data.
In a third aspect, an electronic device is provided, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;
a memory for storing a computer program;
And the processor is used for realizing the ladle slag skimming control method according to any one embodiment of the first aspect when executing the program stored in the memory.
In a fourth aspect, a computer readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, implements a ladle slag control method according to any one of the embodiments of the first aspect.
Compared with the prior art, the technical scheme provided by the embodiment of the application has the following advantages:
According to the embodiment of the application, the linear prediction and the nonlinear prediction are respectively carried out on the basis of the slag-raking input data to obtain the linear slag-raking prediction data and the nonlinear slag-raking prediction data, so that the target prediction data corresponding to the slag-raking input data is determined by adopting the linear slag-raking prediction data and the nonlinear slag-raking prediction data, the slag-raking control can be carried out on the steel ladle according to the target prediction data, the slag-raking data is not required to be determined manually in the slag-raking process, and the accuracy and the efficiency of slag-raking are improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, and it will be obvious to a person skilled in the art that other drawings can be obtained from these drawings without inventive effort.
Fig. 1 is a schematic flow chart of a ladle slag skimming control method according to an embodiment of the present application;
Fig. 2 is a schematic structural diagram of a slag skimming control device for a ladle according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Tilting the ladle to a preset angle during the specific operation process of slag skimming, and then skimming impurities on the surface of molten metal in the ladle; wherein, when the slag-raking modes needed to be adopted in different conditions, such as different liquid levels of the steel ladle, the tilting angles needed by slag raking at the moment are different, or when the slag thickness in the steel ladle is different, the slag raking times or slag raking time needed at the moment are also different; the existing automatic slag skimming also has a semi-automatic slag skimming mode, such as automatic ladle tilting to a certain angle, manual angle adjustment is performed, manual operation is performed to finish slag skimming by observing the liquid level through naked eyes after slag skimming is finished, manual auxiliary operation is required to effectively finish slag skimming operation, and the manual auxiliary operation can enable slag skimming efficiency to be low.
In order to solve the problem that the slag removing efficiency is low due to manual auxiliary operation in the prior art, the embodiment of the application obtains the slag removing input data of the steel ladle, respectively carries out linear prediction and nonlinear prediction based on the slag removing input data to obtain linear slag removing prediction data and nonlinear slag removing prediction data, and determines target prediction data corresponding to the slag removing input data by adopting the linear slag removing prediction data and the nonlinear slag removing prediction data, so that slag removing control can be carried out on the steel ladle according to the target prediction data, and the slag removing data is not required to be determined manually in the slag removing process, thereby improving the accuracy and efficiency of slag removing.
Fig. 1 is a schematic flow chart of a ladle slag skimming control method according to an embodiment of the present application.
As shown in fig. 1, the present application discloses an embodiment, which provides a method for controlling slag skimming of a ladle, comprising:
Step S110: and obtaining the slagging-off input data of the ladle.
The ladle can refer to a ladle which is required to carry out slag skimming operation at present, the ladle represents a container for containing molten metal, and slag skimming input data represents state information of the current ladle and can comprise parameter information such as Bao Ling, arrival tare weight, arrival net weight, liquid level height, arrival slag thickness, outbound slag thickness and the like of the ladle; the method for acquiring the slagging-off input data of the ladle can be a method of user input, sensor acquisition and the like.
Step S120: and respectively carrying out linear prediction and nonlinear prediction based on the slag-raking input data to obtain linear slag-raking prediction data and nonlinear slag-raking prediction data.
Specifically, in this embodiment, after the input data of slag skimming is obtained, linear prediction and nonlinear prediction may be performed based on the input data of slag skimming, so as to perform real-time linear prediction and nonlinear prediction on the slag skimming process of the ladle according to the input data of slag skimming, so as to obtain linear slag skimming prediction data and nonlinear slag skimming prediction data corresponding to the input data of slag skimming; the linear prediction means that linear logic prediction is performed on the slagging process according to the slagging input data, for example, linear equations, coefficient relationships and other modes can be used for prediction, and the embodiment is not particularly limited thereto, and the linear slagging prediction data means data obtained after linear prediction is performed on the slagging process according to the slagging input data; the nonlinear prediction means that nonlinear logic prediction is performed on the slagging process according to the slagging input data, for example, prediction can be performed by using a random forest regression, gradient lifting regression, a BP neural network model, XGBoost algorithm and other modes, and the embodiment is not particularly limited to this, and the linear slagging prediction data means data obtained after linear prediction is performed on the slagging process according to the slagging input data.
It should be noted that one or more data parameters may be included in the linear slag-off prediction data and the nonlinear slag-off prediction data, and the types of the data parameters included in the linear slag-off prediction data and the nonlinear slag-off prediction data may be identical, for example, the slag-off start angle parameter, the slag-off end angle parameter, the slag-off duration parameter, the slag-off frequency parameter, and the like may be included in each of the linear slag-off prediction data and the nonlinear slag-off prediction data.
Step S130: and determining target prediction data corresponding to the slag-raking input data by adopting the linear slag-raking prediction data and the nonlinear slag-raking prediction data.
Specifically, after the linear slag-off prediction data and the nonlinear slag-off prediction data are obtained, the linear slag-off prediction data and the nonlinear slag-off prediction data can be adopted to perform preset calculation processing, so that target prediction data corresponding to slag-off input data is determined; the preset calculation process may be to calculate an average value or a variance value of various data parameters in the linear slag-off prediction data and the nonlinear slag-off prediction data, so that a data parameter set after the calculation process may be used as target prediction data.
Because the slagging-off input data of the steel ladle represent the current state of the steel ladle, and the slagging-off modes required to be adopted by different states of the steel ladle are different, the direct and accurate linear relation is not provided, namely if single linear calculation or linear prediction is adopted, prediction data which is matched with the slagging-off input data cannot be obtained; in addition, because the precision of nonlinear prediction, the requirements on training samples and data precision are high, if single nonlinear calculation or linear prediction is adopted, prediction data which is very matched with the slagging-off input data cannot be accurately and effectively obtained;
non-linear prediction employing linear prediction and machine learning has some advantages:
(1) And (3) improving the robustness and the accuracy: combining the linear model and the nonlinear model may make up for the drawbacks of the respective models. The linear model may not capture complex nonlinear relationships in the data, but works well for some linear relationships; while non-linear models may be more suitable for capturing complex patterns and features, providing more accurate predictions.
(2) Flexibility and interpretability: the interpretability and simplicity of the linear model can be exploited while combining the flexibility of the nonlinear model. This allows some degree of model interpretation to be maintained while more complex data relationships are captured using non-linear models.
(3) Reducing the risk of overfitting: the linear model is relatively simple and less likely to perform well on training data but not on test data due to overfitting. Meanwhile, the nonlinear model can be better adapted to the complexity of data, and the generalization capability of the whole model is improved.
(4) Adaptability to specific situations: in some particular cases, the data may have both linear and non-linear characteristics. At this time, the adoption of both linear and nonlinear predictions can better accommodate the diversity and complexity of the data.
Therefore, in the embodiment, two means of linear prediction and nonlinear prediction are combined, linear slag-raking prediction data and nonlinear slag-raking prediction data are obtained through linear prediction and nonlinear prediction, and then target prediction data is obtained after calculation processing is carried out on the linear slag-raking prediction data and the nonlinear slag-raking prediction data of the two prediction data, and at the moment, the target prediction data is data of the two prediction data of the linear slag-raking prediction data and the nonlinear slag-raking prediction data, so that the degree of fit between the target prediction data and slag-raking input data is improved.
Step S140: and carrying out slag skimming control on the steel ladle according to the target prediction data.
Specifically, after determining the target prediction data, performing slag-raking control on the ladle according to the target prediction data, wherein a specific control mode can be that a control instruction is generated according to the target prediction data, and the control instruction is used for controlling slag-raking equipment to perform slag-raking operation on the ladle; in the embodiment, the slag skimming control process does not need to manually determine slag skimming parameters, but determines target prediction data through linear prediction and nonlinear prediction, so that the problems that the prior art inevitably needs to consume longer time in the process of manually determining the slag skimming parameters, and the probability of judging errors is higher, namely that the accuracy and the efficiency are lower in manually determining the slag skimming parameters are solved. The effect of effectively improving the accuracy and efficiency of slag skimming is achieved.
In an alternative embodiment of the present application, step S110 obtains the slagging-off input data of the ladle, which may specifically include the following sub-steps: acquiring Bao Ling parameters, arrival tare weight parameters, arrival net weight parameters, liquid level height parameters, arrival slag thickness parameters and outbound slag thickness parameters of a ladle; and generating slag skimming input data by adopting the packet age parameter, the arrival weight parameter, the arrival net weight parameter, the liquid level height parameter, the arrival slag thickness parameter and the outbound slag thickness parameter.
Specifically, after determining the ladle needing to perform the slag removing operation, data parameters such as Bao Ling parameters, arrival weight parameters, arrival net weight parameters, liquid level height parameters, arrival slag thickness parameters, and outbound slag thickness parameters of the ladle can be collected, and a specific collection mode can be modes such as user input, sensor collection, database acquisition and the like, and the embodiment is not limited specifically herein.
In an alternative embodiment of the present application, the linear prediction based on the slagging-off input data included in step S120 may specifically include the following sub-steps: acquiring a preset linear regression parameter; performing linear prediction by adopting the linear regression parameters and the slag-raking input data to obtain a first slag-raking start angle parameter, a first slag-raking end angle parameter, a first slag-raking duration parameter and a first slag-raking frequency parameter; and determining the first slag-raking start angle parameter, the first slag-raking end angle parameter, the first slag-raking duration parameter and the first slag-raking times parameter as linear slag-raking prediction data.
Specifically, in the process of performing linear prediction based on the slagging-off input data, a preset linear regression parameter may be obtained, where the linear round parameter may represent a parameter preset to perform linear prediction; the method comprises the steps of carrying out linear prediction by adopting linear regression parameters and slag-raking input data, wherein the linear prediction can be carried out by combining the linear regression parameters and the slag-raking input data, and further obtaining a first slag-raking start angle parameter, a first slag-raking end angle parameter, a first slag-raking duration parameter and a first slag-raking frequency parameter according to calculation results, wherein the first slag-raking start angle parameter represents a tilting angle required by ladle to start slag-raking, the first slag-raking end angle parameter represents a tilting angle when the ladle finishes slag-raking, the first slag-raking duration parameter represents the duration of ladle slag-raking, and the first slag-raking frequency parameter represents the frequency of ladle slag-raking; the first slag-off start angle parameter, the first slag-off end angle parameter, the first slag-off duration parameter, and the first slag-off times parameter may be determined as linear slag-off prediction data.
In a specific embodiment, when the linear prediction is a linear regression equation, the slagging-off input data includes a packet age (x 1), an arrival dead weight (x 2), an arrival net weight (x 3), a liquid level height (x 4), an arrival slag thickness (x 5), and an outbound slag thickness (x 6), the obtaining of the preset linear regression parameters includes calculating coefficients a 0～a4、b0～b7、c0～c6 and d 0～d6, and the linear prediction is performed by using the linear regression parameters and the slagging-off input data: construction of the linear regression equation ：y1＝a0+a1x1+a2x2+a3x3+a4x4; by the first slag-off start angle parameter (y 1) since there is also a significant relationship between the first slag-off start angle parameter and the first slag-off end angle parameter, when constructing the linear regression equation for the first slag-off end angle parameter (y 2), the first slag-off start angle parameter (y 1) may also be used as an argument ：y2＝b0+b1x1+b2x2+b3x3+b4x4+b5x5+b6x6+b7y1; to construct the linear regression equation ：y3＝c0+c1x1+c2x2+c3x3+c4x4+c5x5+c6x6; for the first slag-off duration parameter (y 3) to construct the linear equation for the first slag-off times parameter (y 4):
y4＝d0+d1x1+d2x2+d3x3+d4x4+d5x5+d6x6; And calculating according to the linear regression equation to obtain a first slag-raking start angle parameter, a first slag-raking end angle parameter, a first slag-raking duration parameter and a first slag-raking frequency parameter, and further determining the first slag-raking start angle parameter, the first slag-raking end angle parameter, the first slag-raking duration parameter and the first slag-raking frequency parameter as linear slag-raking prediction data.
In an optional embodiment of the present application, the step S120 includes performing nonlinear prediction based on the slagging-off input data to obtain nonlinear slagging-off prediction data, which may specifically include the following sub-steps: inputting the slagging-off input data into a pre-trained nonlinear prediction model to predict, so as to obtain an output result of the nonlinear prediction model; extracting a second slag-raking start angle parameter, a second slag-raking end angle parameter, a second slag-raking duration parameter and a second slag-raking frequency parameter from the output result; and determining the second slag skimming start angle parameter, the second slag skimming end angle parameter, the second slag skimming duration parameter and the second slag skimming times parameter as nonlinear slag skimming prediction data.
Specifically, in the process of linear prediction based on the slagging-off input data, the slagging-off input data can be input into a pre-trained nonlinear prediction model for prediction, and model calculation is performed through the nonlinear prediction model, so that an output result of the nonlinear prediction model is obtained, wherein the nonlinear prediction model can be a model such as Lasso regression, ridge regression, L1 regular & L2 regular, elastic network regression, bayesian Ridge regression, huber regression, KNN, SVM, decision tree regression, random forest regression, gradient lifting regression, BP neural network model, XGBoost algorithm and the like; further, a second slag-raking start angle parameter, a second slag-raking end angle parameter, a second slag-raking duration parameter and a second slag-raking frequency parameter can be extracted from the output result, and the second slag-raking start angle parameter, the second slag-raking end angle parameter, the second slag-raking duration parameter and the second slag-raking frequency parameter are determined to be nonlinear slag-raking prediction data; the second slag-raking start angle parameter, the second slag-raking end angle parameter, the second slag-raking duration parameter and the second slag-raking frequency parameter are similar to the first slag-raking start angle parameter, the first slag-raking end angle parameter, the first slag-raking duration parameter and the first slag-raking frequency parameter, the second slag-raking start angle parameter represents a tilting angle required by the ladle to start raking, the second slag-raking end angle parameter represents a tilting angle when the ladle finishes raking, the second slag-raking duration parameter represents the duration of ladle slag raking, and the second slag-raking frequency parameter represents the number of ladle slag raking.
In specific implementation, by acquiring historical data of ladle slag-off operation as a training sample set, the historical data can comprise historical slag-off input data and historical slag-off result data, and a preset model is trained by using the training sample set to obtain a nonlinear prediction model. The input layer of the nonlinear prediction model is the ladle age (x 1), the arrival dead weight (x 2), the arrival net weight (x 3), the liquid level height (x 4), the arrival slag thickness (x 5) and the outbound slag thickness (x 6) of the ladle, and the output layer of the nonlinear prediction model is the second slag skimming start angle parameter (y 1), the second slag skimming end angle parameter (y 2), the second slag skimming duration parameter (y 3) and the second slag skimming times parameter (y 4).
In an alternative embodiment of the present application, the step S130 uses linear slagging-off prediction data and nonlinear slagging-off prediction data to determine target prediction data corresponding to the slagging-off input data, which may specifically include the following sub-steps: calculating by adopting linear slag-off prediction data and nonlinear slag-off prediction data to obtain a slag-off prediction data average value; and determining target prediction data based on the average value of the slag-off prediction data.
Specifically, in the process of determining target prediction data corresponding to the slag-raking input data, a first slag-raking start angle parameter, a first slag-raking end angle parameter, a first slag-raking duration parameter and a first slag-raking frequency parameter may be extracted from the linear slag-raking prediction data, and a second slag-raking start angle parameter, a second slag-raking end angle parameter, a second slag-raking duration parameter and a second slag-raking frequency parameter may be extracted from the nonlinear slag-raking prediction data; generating a target slag-off end angle parameter according to the first slag-off end angle parameter and the second slag-off end angle parameter, generating a target slag-off start angle parameter according to the first slag-off start angle parameter and the second slag-off start angle parameter, generating a target slag-off duration parameter according to the first slag-off duration parameter and the second slag-off duration parameter, and generating a target slag-off number parameter according to the first slag-off number parameter and the second slag-off number parameter, wherein the average value in the above process can be calculated, that is, the target slag-off end angle parameter represents the average value of the first slag-off end angle parameter and the second slag-off end angle parameter, the target slag-off start angle parameter represents the average value of the first slag-off duration parameter and the second slag-off duration parameter, and the target slag-off number parameter represents the average value of the first slag-off number parameter and the second slag-off number parameter; that is, the average value of the slag-off prediction data may include a target slag-off end angle parameter, a target slag-off start angle parameter, a target slag-off duration parameter, and a target slag-off times parameter; more specifically, the calculation of the average value of the slag-off predicted data may include two average value calculations, where the first average value calculation is performed to obtain the target slag-off end angle parameter, the target slag-off start angle parameter, the target slag-off duration parameter, and the target slag-off number of times parameter, and then remove each parameter data that the average value of the slag-off predicted data deviates from the target slag-off end angle parameter, the target slag-off start angle parameter, the target slag-off duration parameter, and the target slag-off number of times parameter by more than one standard deviation, and the remaining parameter data is performed to perform a second average value calculation, where the target slag-off end angle parameter, the target slag-off start angle parameter, the target slag-off duration parameter, and the target slag-off number of times parameter obtained by the average value calculation are used as the average value of the slag-off predicted data, and the average value of the slag-off predicted data may be used to determine the target predicted data.
In addition, in the embodiment, the calculation is performed by using the linear slag-off prediction data and the nonlinear slag-off prediction data, so that the average value of the slag-off prediction data is only an example of the feasibility, and other stacking models can be adopted in the concrete implementation; wherein the stacking model is: training is performed on multiple models, and then the predictions of these models are combined using another model (called a meta-model). The linear model may be used as one of the basic models and its prediction results combined with other more complex nonlinear models.
It should be noted that, due to the instability of the single nonlinear prediction model, in this embodiment, the slagging-off input data may be input into at least two nonlinear prediction models trained in advance to perform prediction, so as to obtain at least two nonlinear slagging-off prediction data, that is, the foregoing target prediction data determining process may be performed according to at least one linear slagging-off prediction data and at least two nonlinear slagging-off prediction data to calculate, so as to obtain a slagging-off prediction data average value. And the average value accuracy of the final slag skimming prediction data is improved.
Also, the adoption of two or more non-linear prediction methods based on machine learning to jointly predict results has the following reasons and advantages:
(1) Robustness and accuracy are improved: different machine learning models may have different advantages in capturing data patterns and features. By combining the prediction results of multiple models, the deviation of a single model can be reduced, thereby improving the accuracy of overall prediction. Even if one model does not perform well in some cases, the prediction results of other models can make up for the deficiency, and the overall prediction robustness is improved.
(2) Reducing the risk of overfitting: the use of multiple different types of models for prediction may reduce the risk of overfitting. If a certain model is too sensitive to training data, an overfitting may result. By combining multiple models, the overfitting of a single model to specific data can be reduced, and the generalization capability of the model can be improved.
(3) Providing a wide variety of viewing angles: different machine learning models may use different feature representations and learning methods, and thus may provide a variety of data perspectives. This diversity helps to capture the different patterns and structures in the data, providing a more comprehensive prediction.
(4) Model bias should be taken: different models may have different deviations from the data, and combining multiple models may compensate for the deviation of a single model to some extent. This may increase the robustness of the model and reduce prediction errors due to limitations of a single model.
In an alternative embodiment of the present application, step S140 performs slag-off control on the ladle according to the target prediction data, and may specifically include the following sub-steps: generating a control instruction of the slag removing device according to the target prediction data; based on the control instruction, carrying out slag skimming treatment on the steel ladle through slag skimming equipment, and acquiring real-time slag skimming parameters of the slag skimming equipment; and generating slag-raking ending information under the condition that the real-time slag-raking parameters meet ending conditions corresponding to the target prediction parameters.
Specifically, in the process of performing slag-off control on the ladle in the embodiment, a control instruction of a slag-off device may be generated according to target prediction data, where the slag-off device represents a device for performing slag-off processing on the ladle, and the control instruction represents an instruction for controlling the slag-off device; the process of generating control may be to extract a target slag-raking start angle parameter, a target slag-raking end angle parameter, a target slag-raking duration parameter, and a target slag-raking number parameter from target prediction data, and generate a control instruction according to the target slag-raking start angle parameter, the target slag-raking end angle parameter, the target slag-raking duration parameter, and the target slag-raking number parameter; the ladle can be subjected to slag-removing treatment according to the control instruction by the slag-removing equipment, and real-time slag-removing parameters of the slag-removing equipment are acquired in real time, wherein the real-time slag-removing parameters represent the current state of the slag-removing equipment, such as real-time slag-removing angle parameters, real-time slag-removing duration parameters and real-time slag-removing frequency parameters, the real-time slag-removing angle parameters represent the current tipping angle of the slag-removing ladle, the real-time slag-removing duration parameters represent the current slag-removing frequency; judging whether the real-time slag skimming parameter accords with an ending condition corresponding to the target prediction parameter, wherein the ending condition is a condition for stopping slag skimming operation, and the ending condition can be determined according to the target prediction parameter; under the condition that the real-time slag-off parameters meet the end conditions corresponding to the target prediction parameters, slag-off end information is generated, the condition that slag-off operation is stopped is described to be met, at the moment, the output of a control instruction or a stop instruction can be stopped, the control instruction is output and used for controlling slag-off equipment to stop slag-off, and slag-off end information is further generated, wherein the slag-off end information represents the state of a ladle at the end of slag-off, namely, the real-time slag-off parameters acquired at the end of slag-off.
In an optional embodiment of the present application, the target prediction data includes a target slag-off end angle parameter, a target slag-off duration parameter, and a target slag-off frequency parameter, and the real-time slag-off parameter includes a real-time slag-off angle parameter, a real-time slag-off duration parameter, and a real-time slag-off frequency parameter; after the real-time slag skimming parameters of the slag skimming device are obtained, the method can further comprise the following substeps: determining that the real-time slag skimming parameter meets the ending condition corresponding to the target predicted parameter under the condition that the real-time slag skimming angle parameter reaches the target slag skimming ending angle parameter and the real-time slag skimming duration parameter reaches the target slag skimming duration parameter; or determining that the real-time slag skimming parameter meets the ending condition corresponding to the target predicted parameter under the condition that the real-time slag skimming angle parameter reaches the target slag skimming ending angle parameter and the real-time slag skimming frequency parameter reaches the target slag skimming frequency parameter; or determining that the real-time slag skimming parameter meets the ending condition corresponding to the target predicted parameter under the condition that the real-time slag skimming frequency parameter reaches the target slag skimming frequency parameter and the real-time slag skimming duration parameter reaches the target slag skimming duration parameter.
In this embodiment, after extracting the target slag-off angle parameter, the target slag-off duration parameter, and the target slag-off frequency parameter in the target prediction data, and extracting the real-time slag-off angle parameter, the real-time slag-off duration parameter, and the real-time slag-off frequency parameter in the real-time slag-off parameters, respectively determining whether the real-time slag-off angle parameter reaches the target slag-off angle parameter, whether the real-time slag-off duration parameter reaches the target slag-off duration parameter, and whether the real-time slag-off frequency parameter reaches the target slag-off frequency parameter, and determining that the real-time slag-off parameter meets the end condition corresponding to the target prediction parameter if at least two of the above determination results belong to the achievement; namely, under the condition that the real-time slag-raking angle parameter reaches the target slag-raking end angle parameter and the real-time slag-raking duration parameter reaches the target slag-raking duration parameter, determining that the real-time slag-raking parameter meets the end condition corresponding to the target predicted parameter; or determining that the real-time slag skimming parameter meets the ending condition corresponding to the target predicted parameter under the condition that the real-time slag skimming angle parameter reaches the target slag skimming ending angle parameter and the real-time slag skimming frequency parameter reaches the target slag skimming frequency parameter; or determining that the real-time slag skimming parameter meets the ending condition corresponding to the target predicted parameter under the condition that the real-time slag skimming frequency parameter reaches the target slag skimming frequency parameter and the real-time slag skimming duration parameter reaches the target slag skimming duration parameter.
In an alternative embodiment of the present application, after the slag-off control is performed on the ladle according to the target prediction data in S140, the method may further include the following sub-steps: acquiring slag-off ending parameters of the steel ladle based on the slag-off ending information; under the condition that the slag skimming end parameter meets the preset condition, updating a training sample set of the nonlinear prediction model by adopting the slag skimming end parameter and slag skimming input data, and determining the updating quantity of the training sample set; under the condition that the update quantity reaches a preset update quantity threshold value, retraining the nonlinear prediction model by adopting sample data in a training sample set, wherein the sample data comprises a slag removing ending parameter and slag removing input data.
Specifically, after the ladle is subjected to slag-off control, slag-off ending information can be obtained, slag-off ending parameters of the ladle are obtained according to the slag-off ending information, and the slag-off ending parameters represent the state when the ladle finishes slag-off; judging whether the slag-off ending parameter meets a preset condition, wherein the preset condition represents a preset state of the ladle after slag-off is ended, for example, the preset condition can comprise an impurity residual quantity parameter threshold and a splashing liquid parameter threshold when the slag-off ending parameter comprises an impurity residual quantity parameter and a splashing liquid parameter, and the slag-off ending parameter can be determined to meet the preset condition when the impurity residual quantity parameter is lower than the impurity residual quantity parameter threshold and the splashing liquid parameter is lower than the splashing liquid parameter threshold; under the condition that the slag skimming end parameter meets the preset condition, the slag skimming end parameter and slag skimming input data can be adopted to update the training sample set of the nonlinear prediction model, and the slag skimming end parameter and the slag skimming input data can be replaced by the training sample with the earliest timestamp in the training sample set in a concrete updating mode, so that the number of training samples in the training sample set is kept unchanged; the updating quantity of the training sample set can be determined, the updating quantity represents the quantity of the slag raking ending parameter and the slag raking input data updated to the training sample set, whether the updating quantity reaches a preset updating quantity threshold value is further judged, and under the condition that the updating quantity reaches the preset updating quantity threshold value, the sample data in the training sample set is adopted to retrain the nonlinear prediction model, wherein the sample data comprises the slag raking ending parameter and the slag raking input data; so that the nonlinear predictive model in the present embodiment can continuously retrain the nonlinear predictive model using the updated training sample set, and can play a role in controlling the frequency of retraining the nonlinear predictive model by updating the number threshold.
It should be noted that, when the update number reaches the preset update number threshold, the linear regression parameters and the corresponding linear equations in the foregoing embodiments may be reconstructed according to the sample data in the training sample set, so as to perform linear prediction by using the reconstructed linear regression parameters and the reconstructed linear equations to correspond to the slagging-off input data.
As shown in fig. 2, the present application further discloses an embodiment, which provides a slag skimming control device for a ladle, including:
An acquisition module 210, configured to acquire slagging-off input data of a ladle;
the prediction module 220 is configured to perform linear prediction and nonlinear prediction based on the slagging-off input data, to obtain linear slagging-off prediction data and nonlinear slagging-off prediction data;
The determining module 230 is configured to determine target prediction data corresponding to the slagging-off input data by using the linear slagging-off prediction data and the nonlinear slagging-off prediction data;
The control module 240 is configured to perform slag-off control on the ladle according to the target prediction data.
In one embodiment, the prediction module 220 may include:
The first acquisition unit is used for acquiring preset linear regression parameters;
The first prediction unit is used for performing linear prediction by adopting the linear regression parameter and the slag-raking input data to obtain a first slag-raking start angle parameter, a first slag-raking end angle parameter, a first slag-raking duration parameter and a first slag-raking frequency parameter;
The first determining unit is used for determining the first slag skimming start angle parameter, the first slag skimming end angle parameter, the first slag skimming duration parameter and the first slag skimming frequency parameter as linear slag skimming prediction data.
In one embodiment, the prediction module 220 may include:
the second prediction unit is used for inputting the slagging-off input data into a pre-trained nonlinear prediction model to perform prediction, so as to obtain an output result of the nonlinear prediction model;
The first extraction unit is used for extracting a second slag skimming start angle parameter, a second slag skimming end angle parameter, a second slag skimming duration parameter and a second slag skimming frequency parameter from the output result;
The second determining unit is used for determining the second slag skimming start angle parameter, the second slag skimming end angle parameter, the second slag skimming duration parameter and the second slag skimming frequency parameter as nonlinear slag skimming prediction data.
In one embodiment, the determining module 230 may include:
the first calculation unit is used for calculating by adopting linear slag-off prediction data and nonlinear slag-off prediction data to obtain a slag-off prediction data average value;
and a third determining unit for determining target prediction data based on the average value of the slag-off prediction data.
In one embodiment, the control module 240 may include:
The first generation unit is used for generating a control instruction of the slag removing device according to the target prediction data;
the acquisition unit is used for carrying out slag-raking treatment on the steel ladle through slag-raking equipment based on the control instruction and acquiring real-time slag-raking parameters of the slag-raking equipment;
And the second generation unit is used for generating slag-raking ending information under the condition that the real-time slag-raking parameters meet the ending conditions corresponding to the target prediction parameters.
In an embodiment, the target prediction data includes a target slag-off end angle parameter, a target slag-off duration parameter, and a target slag-off frequency parameter, and the real-time slag-off parameters include a real-time slag-off angle parameter, a real-time slag-off duration parameter, and a real-time slag-off frequency parameter; the control module 240 may further include:
A fourth determining unit, configured to determine that the real-time slag-raking parameter meets an end condition corresponding to the target predicted parameter when the real-time slag-raking angle parameter reaches the target slag-raking end angle parameter and the real-time slag-raking duration parameter reaches the target slag-raking duration parameter; or alternatively
A fifth determining unit, configured to determine that the real-time slag-raking parameter meets an end condition corresponding to the target predicted parameter when the real-time slag-raking angle parameter reaches the target slag-raking end angle parameter and the real-time slag-raking frequency parameter reaches the target slag-raking frequency parameter; or alternatively
The sixth determining unit is configured to determine that the real-time slag-removing parameter meets an end condition corresponding to the target predicted parameter when the real-time slag-removing frequency parameter reaches the target slag-removing frequency parameter and the real-time slag-removing duration parameter reaches the target slag-removing duration parameter.
In an embodiment, the apparatus may further include:
the ending module is used for acquiring slag-off ending parameters of the steel ladle based on the slag-off ending information;
The updating module is used for updating the training sample set of the nonlinear prediction model by adopting the slag skimming end parameter and slag skimming input data under the condition that the slag skimming end parameter meets the preset condition, and determining the updating quantity of the training sample set;
the training module is used for retraining the nonlinear prediction model by adopting sample data in a training sample set under the condition that the update number reaches a preset update number threshold value, wherein the sample data comprises a slag-off ending parameter and slag-off input data.
The implementation process of the functions and roles of each module in the above device is specifically shown in the implementation process of the corresponding steps in the above method, and will not be described herein again.
As shown in fig. 3, an embodiment of the present application provides an electronic device including a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, the memory 330 complete communication with each other through the communication bus 340,
A memory 330 for storing a computer program;
in an embodiment of the present application, when executing a program stored in the memory 330, the processor 310 is configured to implement the method for controlling slag removal of a ladle according to any one of the foregoing method embodiments, perform linear prediction and nonlinear prediction based on slag removal input data by acquiring slag removal input data of the ladle, respectively, to obtain linear slag removal prediction data and nonlinear slag removal prediction data, so as to determine target prediction data corresponding to the slag removal input data by using the linear slag removal prediction data and the nonlinear slag removal prediction data, thereby performing slag removal control on the ladle according to the target prediction data, without manually determining slag removal data in the slag removal process, and improving accuracy and efficiency of slag removal.
The embodiment of the application also provides a computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, and when the computer program is executed by a processor, the method for controlling the slag skimming of the ladle is realized, according to any one of the method embodiments, through obtaining slag skimming input data of the ladle, respectively carrying out linear prediction and nonlinear prediction based on the slag skimming input data to obtain linear slag skimming prediction data and nonlinear slag skimming prediction data, and determining target prediction data corresponding to the slag skimming input data by adopting the linear slag skimming prediction data and the nonlinear slag skimming prediction data, thereby carrying out slag skimming control on the ladle according to the target prediction data without manually determining the slag skimming data in the slag skimming process, and improving the accuracy and efficiency of slag skimming.
It should be noted that in this document, relational terms such as "first" and "second" and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing description has been directed to specific embodiments of this specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing is only a specific embodiment of the invention to enable those skilled in the art to understand or practice the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. The ladle slag skimming control method is characterized by comprising the following steps:
Acquiring slag skimming input data of a ladle;
Based on the slagging-off input data, respectively performing linear prediction and nonlinear prediction to obtain linear slagging-off prediction data and nonlinear slagging-off prediction data;
Determining target prediction data corresponding to the slag-raking input data by adopting the linear slag-raking prediction data and the nonlinear slag-raking prediction data;
and carrying out slag skimming control on the steel ladle according to the target prediction data.
2. The method of controlling slag removal from a ladle according to claim 1, wherein performing linear prediction based on the slag removal input data to obtain linear slag removal prediction data comprises:
Acquiring a preset linear regression parameter;
performing linear prediction by adopting the linear regression parameters and the slag-raking input data to obtain a first slag-raking start angle parameter, a first slag-raking end angle parameter, a first slag-raking duration parameter and a first slag-raking frequency parameter;
And determining the first slag skimming start angle parameter, the first slag skimming end angle parameter, the first slag skimming duration parameter and the first slag skimming frequency parameter as the linear slag skimming prediction data.
3. The method of controlling slag removal from a ladle according to claim 1, wherein the non-linear prediction is performed based on the slag removal input data to obtain non-linear slag removal prediction data, comprising:
Inputting the slagging-off input data into a pre-trained nonlinear prediction model to predict, and obtaining an output result of the nonlinear prediction model;
Extracting a second slag skimming start angle parameter, a second slag skimming end angle parameter, a second slag skimming duration parameter and a second slag skimming frequency parameter from the output result;
and determining the second slag skimming start angle parameter, the second slag skimming end angle parameter, the second slag skimming duration parameter and the second slag skimming frequency parameter as the nonlinear slag skimming prediction data.
4. The method for controlling slag removal from a steel ladle according to claim 1, wherein determining target prediction data corresponding to the slag removal input data using the linear slag removal prediction data and the nonlinear slag removal prediction data comprises:
Calculating by adopting the linear slag-off prediction data and the nonlinear slag-off prediction data to obtain a slag-off prediction data average value;
and determining the target prediction data based on the average value of the slag skimming prediction data.
5. The method of controlling slag removal from a ladle according to claim 1, wherein said controlling slag removal from the ladle in accordance with the target prediction data comprises:
Generating a control instruction of the slag removing device according to the target prediction data;
based on the control instruction, carrying out slag skimming treatment on the steel ladle through slag skimming equipment, and acquiring real-time slag skimming parameters of the slag skimming equipment;
And generating slag-raking ending information under the condition that the real-time slag-raking parameters meet the ending conditions corresponding to the target prediction parameters.
6. The method according to claim 5, wherein the target prediction data includes a target slag-off end angle parameter, a target slag-off duration parameter, and a target slag-off frequency parameter, and the real-time slag-off parameters include a real-time slag-off angle parameter, a real-time slag-off duration parameter, and a real-time slag-off frequency parameter;
After the real-time slag skimming parameters of the slag skimming device are obtained, the method further comprises the following steps:
Determining that the real-time slag skimming parameter meets the ending condition corresponding to the target prediction parameter under the condition that the real-time slag skimming angle parameter reaches the target slag skimming ending angle parameter and the real-time slag skimming duration parameter reaches the target slag skimming duration parameter; or alternatively
Determining that the real-time slag skimming parameter meets the ending condition corresponding to the target prediction parameter under the condition that the real-time slag skimming angle parameter reaches the target slag skimming ending angle parameter and the real-time slag skimming frequency parameter reaches the target slag skimming frequency parameter; or alternatively
And determining that the real-time slag skimming parameter meets the ending condition corresponding to the target prediction parameter under the condition that the real-time slag skimming frequency parameter reaches the target slag skimming frequency parameter and the real-time slag skimming duration parameter reaches the target slag skimming duration parameter.
7. The method of controlling slag removal from a ladle as recited in claim 5, further comprising, after said slag removal control of said ladle based on said target prediction data:
acquiring slag-off ending parameters of the steel ladle based on the slag-off ending information;
Under the condition that the slag skimming end parameter meets the preset condition, updating a training sample set of a nonlinear prediction model by adopting the slag skimming end parameter and the slag skimming input data, and determining the updating quantity of the training sample set;
And under the condition that the update quantity reaches a preset update quantity threshold value, retraining the nonlinear prediction model by adopting sample data in the training sample set, wherein the sample data comprises the slagging-off ending parameter and the slagging-off input data.
8. A slag skimming control device for a ladle, comprising:
The acquisition module is used for acquiring the slagging-off input data of the ladle;
the prediction module is used for respectively carrying out linear prediction and nonlinear prediction based on the slag-raking input data to obtain linear slag-raking prediction data and nonlinear slag-raking prediction data;
The determining module is used for determining target prediction data corresponding to the slag-raking input data by adopting the linear slag-raking prediction data and the nonlinear slag-raking prediction data;
and the control module is used for carrying out slag skimming control on the steel ladle according to the target prediction data.
9. The electronic equipment is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
a memory for storing a computer program;
A processor for implementing the ladle slag removal control method according to any one of claims 1 to 7 when executing a program stored in a memory.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements a ladle slag control method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410035215.0A CN118072876A (en) | 2024-01-09 | 2024-01-09 | Ladle slag skimming control method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410035215.0A CN118072876A (en) | 2024-01-09 | 2024-01-09 | Ladle slag skimming control method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118072876A true CN118072876A (en) | 2024-05-24 |
Family
ID=91106659
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410035215.0A Pending CN118072876A (en) | 2024-01-09 | 2024-01-09 | Ladle slag skimming control method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118072876A (en) |
-
2024
- 2024-01-09 CN CN202410035215.0A patent/CN118072876A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP2020041290A (en) | Optimal compaction determination construction system for concrete | |
| WO2020152750A1 (en) | Design assistance method for metal material, prediction model generation method, metal material manufacturing method, and design assistance device | |
| CN111126206B (en) | Smelting state detection system and method based on deep learning | |
| CN113192568A (en) | Refining furnace desulfurization terminal point forecasting method and system | |
| JP5363238B2 (en) | Output value prediction method, apparatus, and program for the method | |
| CN112731981B (en) | Automatic remote control system of water conservancy gate | |
| CN117468085B (en) | Crystal bar growth control method and device, crystal growth furnace system and computer equipment | |
| CN112465223A (en) | Blast furnace temperature state prediction method | |
| CN110598958A (en) | Steel ladle grading management analysis method and system | |
| CN118072876A (en) | Ladle slag skimming control method and device, electronic equipment and storage medium | |
| JP2018070926A (en) | Electric furnace operation control system, electric furnace, and electric furnace operation control method | |
| CN107052320A (en) | Auto-pouring System and sprue cup liquid level recognition methods based on image detection | |
| CN111334636B (en) | Converter end point dynamic control method and system based on sublance detection | |
| JP2007052739A (en) | Method and device for generating model, method and device for predicting state, and method and system for adjusting state | |
| JP2022039443A (en) | Information processing device, information processing method, and program | |
| CN117187943A (en) | Melt detection method and device in crystal pulling process and electronic equipment | |
| CN103194574B (en) | Dynamic regulation method of VOD refined end point carbon content prediction model | |
| JP7401752B2 (en) | Model construction device, prediction device, model construction method, prediction method, and computer program | |
| CN115271626A (en) | Abnormity monitoring method for electrolytic production | |
| CN112828275A (en) | Automatic slag skimming method, device and system | |
| JP2012226732A (en) | Operation prediction apparatus, operation prediction method and computer program | |
| CN115082734B (en) | Aluminum electrolysis cell fire eye video inspection system and superheat degree deep learning identification method | |
| CN115576285A (en) | Full-automatic production method and system for LF refining | |
| JP7156023B2 (en) | Continuous casting operation support device, continuous casting operation support method, and program | |
| CN112853033A (en) | Efficient slag splashing intelligent control method and system based on furnace mouth image analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |