CN117828900B - Impurity removal reminding method, system and medium applied to slab rolling - Google Patents
Impurity removal reminding method, system and medium applied to slab rolling Download PDFInfo
- Publication number
- CN117828900B CN117828900B CN202410240867.8A CN202410240867A CN117828900B CN 117828900 B CN117828900 B CN 117828900B CN 202410240867 A CN202410240867 A CN 202410240867A CN 117828900 B CN117828900 B CN 117828900B
- Authority
- CN
- China
- Prior art keywords
- rolling
- slab
- quality evaluation
- information
- model
- 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.)
- Active
Links
- 238000005096 rolling process Methods 0.000 title claims abstract description 454
- 239000012535 impurity Substances 0.000 title claims abstract description 116
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000013441 quality evaluation Methods 0.000 claims abstract description 115
- 238000012549 training Methods 0.000 claims description 77
- 238000012795 verification Methods 0.000 claims description 20
- 238000003860 storage Methods 0.000 claims description 13
- 238000000547 structure data Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 7
- 239000000203 mixture Substances 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 abstract description 18
- 239000013078 crystal Substances 0.000 description 4
- 238000001556 precipitation Methods 0.000 description 3
- 229910000831 Steel Inorganic materials 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000009749 continuous casting Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 238000005266 casting Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
Landscapes
- Control Of Metal Rolling (AREA)
Abstract
The embodiment of the application provides an impurity removal reminding method, a system and a medium applied to slab rolling, wherein the method comprises the following steps: acquiring slab parameter information, wherein the slab parameter information comprises slab thickness, slab components and slab metallographic structure; inputting the slab parameter information into a rolling model, and outputting the set rolling parameter information through the rolling model; acquiring real-time rolling state information; analyzing the change data of the slab parameter information based on the real-time rolling state information, inputting a quality evaluation model according to the change data of the slab parameter information, and outputting a rolling product quality evaluation result according to the quality evaluation model; impurity removal information is generated according to quality evaluation results, rolling parameters are generated according to different slab parameters, rolling treatment is conducted on the slab, impurities in the slab are removed, impurity removal effects are judged through analysis of the quality of the rolled product after treatment, and dynamic reminding is conducted, so that rolling flexibility of the slab is improved.
Description
Technical Field
The application relates to the field of slab rolling, in particular to an impurity removal reminding method, system and medium applied to slab rolling.
Background
The slab is a steel billet, is formed by continuous casting of molten steel through a continuous casting machine, is a so-called slab with the width-to-thickness ratio of generally casting blank being larger than 3, is mainly used for rolling a plate, but is not rolled yet, impurities in the slab can be removed in the rolling process, a rolling model is not established in the conventional slab impurity removing method, flexible adjustment of rolling parameters is difficult to carry out through the rolling model, so that the impurity cleaning effect in a rolled product is poor, and in the impurity cleaning process, dynamic reminding cannot be carried out, and the impurity removing precision is affected; in view of the above problems, an effective technical solution is currently needed.
Disclosure of Invention
The embodiment of the application aims to provide an impurity removal reminding method, system and medium applied to slab rolling, which are used for rolling a slab according to rolling parameters generated by different slab parameters so as to remove impurities in the slab, judging impurity removal effects by analyzing the quality of a rolled product after the treatment, and carrying out active reminding to improve the rolling flexibility of the slab.
The embodiment of the application also provides an impurity removal reminding method applied to slab rolling, which comprises the following steps:
Acquiring slab parameter information, wherein the slab parameter information comprises slab thickness, slab components and slab metallographic structure;
inputting the slab parameter information into a rolling model, and outputting the set rolling parameter information through the rolling model;
Rolling the slab according to the set rolling parameter information, and acquiring real-time rolling state information;
Analyzing the change data of the slab parameter information based on the real-time rolling state information, inputting a quality evaluation model according to the change data of the slab parameter information, and outputting a rolling product quality evaluation result according to the quality evaluation model;
And generating impurity removal information according to the quality evaluation result, and transmitting the impurity removal information to a terminal for impurity removal reminding.
Optionally, in the impurity removal reminding method applied to slab rolling according to the embodiment of the present application, the slab parameter information is obtained, which specifically includes:
Collecting slab images, extracting image features, and carrying out normalization processing on the image features to obtain optimized image features;
comparing the optimized image features with the set reference features to obtain feature deviation rates;
judging whether the characteristic deviation rate is larger than or equal to a preset characteristic deviation rate threshold value;
if the image is larger than or equal to the background feature, judging the optimized image feature as the background feature, and eliminating the background feature;
if the thickness of the slab is smaller than the preset value, judging the slab characteristics, acquiring slab edge characteristics according to the slab characteristics, and generating the thickness of the slab.
Optionally, in the impurity removal reminding method applied to slab rolling according to the embodiment of the present application, slab parameter information is input into a rolling model, and set rolling parameter information is output through the rolling model, which specifically includes:
Acquiring slab parameter information to obtain a slab thickness data set, a slab composition data set and a slab metallographic structure data set;
Generating data set proportion information according to the weight information of the slab parameters, calling slab thickness data quantity, slab component data quantity and slab metallographic structure data quantity of corresponding proportion according to the data set proportion information, and generating a training data set;
inputting the training data set into a rolling model for model training to obtain a training result, and judging whether the training result is converged;
If the rolling parameters are converged, outputting the set rolling parameter information according to the rolling model;
if the rolling model is not converged, the proportion of the data set is adjusted, a new training data set is generated, and the rolling model is trained according to the new training data set until the rolling model is converged.
Optionally, in the impurity removal reminding method applied to slab rolling according to the embodiment of the present application, rolling is performed on a slab according to set rolling parameter information, and real-time rolling state information is obtained, which specifically includes:
acquiring rolling parameter information, wherein the rolling parameter information comprises rolling temperature, rolling speed and rolling force;
Analyzing the rolling temperature, rolling speed and rolling force of different time nodes according to the rolling parameter information;
Performing difference calculation on the rolling temperatures of adjacent time nodes to obtain temperature differences;
judging whether the temperature difference is larger than or equal to a set temperature threshold value;
If the rolling temperature is greater than or equal to the preset rolling temperature, adjusting the rolling temperature;
If the rolling state information is smaller than the current rolling temperature, rolling state information is generated according to the current rolling temperature.
Optionally, in the impurity removal reminding method applied to slab rolling according to the embodiment of the present application, the rolling temperature, rolling speed and rolling force of different time nodes are analyzed according to rolling parameter information, and the method further includes:
Acquiring rolling speeds of different time nodes, and analyzing speed change rates according to the rolling speeds of the different time nodes;
analyzing rolling forces corresponding to different time nodes according to the speed change rate, and generating a relation curve of the rolling speed and the rolling forces;
analyzing the variation of the rolling force according to the relation curve of the rolling speed and the rolling force;
Analyzing impurity treatment results according to the variation of rolling force;
judging whether the rolling treatment result meets the requirement;
if the requirements are met, rolling the plate blank according to the current rolling speed and rolling force;
If the rolling speed or rolling force is not satisfied, the rolling speed or rolling force is adjusted.
Optionally, in the impurity removal reminding method applied to slab rolling according to the embodiment of the present application, change data of slab parameter information is analyzed based on real-time rolling state information, the change data of the slab parameter information is input into a quality evaluation model, and a rolled product quality evaluation result is output according to the quality evaluation model, and the method specifically includes:
Acquiring rolling state information of different time nodes, and comparing rolling state information of adjacent time nodes to obtain a state difference value;
calculating the parameter variation of the slab according to the state difference value, and analyzing the parameter variation of the slab according to the quality evaluation model;
If the variable quantity of the slab parameter is larger than the first variable quantity threshold value and smaller than the second variable quantity threshold value, generating first quality evaluation information;
if the variable quantity of the slab parameter is larger than or equal to a second variable quantity threshold value, generating second quality evaluation information;
generating a rolled product quality evaluation result according to the first quality evaluation information and the second quality evaluation information;
The training method of the quality evaluation model comprises the following steps:
generating training data based on the relation between the plate blank parameter change information and the quality evaluation result;
Performing iterative training on the quality evaluation model for a plurality of times according to the training data, and dynamically adjusting model parameters of the quality evaluation model according to the iterative training result;
Randomly extracting training data to establish a verification set, and inputting the verification set into a trained quality evaluation model for verification to obtain a verification result;
And adding constraint conditions to the quality evaluation model based on the verification result to obtain a final quality evaluation model, and analyzing the parameter variation of the slab based on the final quality evaluation model, wherein the constraint conditions comprise the value range of the model parameters or the number of iterative training times.
In a second aspect, an embodiment of the present application provides an impurity removal reminding system applied to slab rolling, the system including: the device comprises a memory and a processor, wherein the memory comprises a program applied to an impurity removal reminding method under slab rolling, and the program applied to the impurity removal reminding method under slab rolling realizes the following steps when being executed by the processor:
Acquiring slab parameter information, wherein the slab parameter information comprises slab thickness, slab components and slab metallographic structure;
inputting the slab parameter information into a rolling model, and outputting the set rolling parameter information through the rolling model;
Rolling the slab according to the set rolling parameter information, and acquiring real-time rolling state information;
Analyzing the change data of the slab parameter information based on the real-time rolling state information, inputting a quality evaluation model according to the change data of the slab parameter information, and outputting a rolling product quality evaluation result according to the quality evaluation model;
And generating impurity removal information according to the quality evaluation result, and transmitting the impurity removal information to a terminal for impurity removal reminding.
Optionally, in the impurity removal reminding system applied to slab rolling according to the embodiment of the present application, the slab parameter information is obtained, which specifically includes:
Collecting slab images, extracting image features, and carrying out normalization processing on the image features to obtain optimized image features;
comparing the optimized image features with the set reference features to obtain feature deviation rates;
judging whether the characteristic deviation rate is larger than or equal to a preset characteristic deviation rate threshold value;
if the image is larger than or equal to the background feature, judging the optimized image feature as the background feature, and eliminating the background feature;
if the thickness of the slab is smaller than the preset value, judging the slab characteristics, acquiring slab edge characteristics according to the slab characteristics, and generating the thickness of the slab.
Optionally, in the impurity removal reminding system applied to slab rolling according to the embodiment of the present application, slab parameter information is input into a rolling model, and set rolling parameter information is output through the rolling model, which specifically includes:
Acquiring slab parameter information to obtain a slab thickness data set, a slab composition data set and a slab metallographic structure data set;
Generating data set proportion information according to the weight information of the slab parameters, calling slab thickness data quantity, slab component data quantity and slab metallographic structure data quantity of corresponding proportion according to the data set proportion information, and generating a training data set;
inputting the training data set into a rolling model for model training to obtain a training result, and judging whether the training result is converged;
If the rolling parameters are converged, outputting the set rolling parameter information according to the rolling model;
if the rolling model is not converged, the proportion of the data set is adjusted, a new training data set is generated, and the rolling model is trained according to the new training data set until the rolling model is converged.
In a third aspect, an embodiment of the present application further provides a computer readable storage medium, where the computer readable storage medium includes an impurity removal reminding method program applied under slab rolling, and when the impurity removal reminding method program applied under slab rolling is executed by a processor, the steps of the impurity removal reminding method applied under slab rolling according to any one of the above steps are implemented.
As can be seen from the above, the impurity removal reminding method, system and medium applied to slab rolling provided by the embodiment of the application are that by obtaining slab parameter information, the slab parameter information comprises slab thickness, slab components and slab metallographic structure; inputting the slab parameter information into a rolling model, and outputting the set rolling parameter information through the rolling model; rolling the slab according to the set rolling parameter information, and acquiring real-time rolling state information; analyzing the change data of the slab parameter information based on the real-time rolling state information, inputting a quality evaluation model according to the change data of the slab parameter information, and outputting a rolling product quality evaluation result according to the quality evaluation model; generating impurity removal information according to the quality evaluation result, and transmitting the impurity removal information to a terminal for impurity removal reminding; and generating rolling parameters according to different slab parameters, rolling the slab, removing impurities in the slab, judging the impurity removal effect by analyzing the quality of the rolled product after the treatment, and carrying out dynamic reminding to improve the rolling flexibility of the slab.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and should not be considered as limiting the scope, and other related drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of an impurity removal reminding method applied to slab rolling according to an embodiment of the present application;
fig. 2 is a flowchart of a slab thickness generating method applied to a reminding method of impurity removal under slab rolling according to an embodiment of the present application;
fig. 3 is a flowchart of a rolling model training method applied to an impurity removal reminding method under slab rolling according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present application.
It should be noted that like reference numerals and letters refer to like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
Referring to fig. 1, fig. 1 is a flowchart of an impurity removal reminding method applied to slab rolling according to some embodiments of the application. The impurity removal reminding method applied to slab rolling is used in terminal equipment and comprises the following steps of:
s101, obtaining slab parameter information, wherein the slab parameter information comprises slab thickness, slab components and slab metallographic structure;
S102, inputting slab parameter information into a rolling model, and outputting set rolling parameter information through the rolling model;
s103, rolling the slab according to the set rolling parameter information, and acquiring real-time rolling state information;
s104, analyzing the change data of the slab parameter information based on the real-time rolling state information, inputting a quality evaluation model according to the change data of the slab parameter information, and outputting a rolling product quality evaluation result according to the quality evaluation model;
S105, generating impurity removal information according to the quality evaluation result, and transmitting the impurity removal information to the terminal for impurity removal reminding.
The rolling model is used for accurately outputting rolling parameters, so that the impurity removal effect in the slab rolling process is improved, the impurity treatment requirement is met when the quality of a rolled product is evaluated, and the impurity treatment precision is improved.
Referring to fig. 2, fig. 2 is a flowchart illustrating a slab thickness generating method applied to a reminding method for impurity removal under slab rolling according to some embodiments of the present application. According to the embodiment of the application, the method for acquiring the slab parameter information comprises the following steps:
s201, collecting slab images, extracting image features, and carrying out normalization processing on the image features to obtain optimized image features;
s202, comparing the optimized image features with set reference features to obtain feature deviation rates;
S203, judging whether the characteristic deviation rate is larger than or equal to a preset characteristic deviation rate threshold value;
S204, if the image is larger than or equal to the background feature, judging the optimized image feature as the background feature, and eliminating the background feature;
And S205, if the thickness of the slab is smaller than the preset value, judging the slab characteristics, acquiring slab edge characteristics according to the slab characteristics, and generating the thickness of the slab.
By analyzing the slab image, the background features and the slab features are accurately screened out, the slab features are independently analyzed, the slab thickness is accurately obtained, and the slab rolling effect is improved.
Referring to fig. 3, fig. 3 is a flowchart of a rolling model training method applied to a reminding method for impurity removal under slab rolling according to some embodiments of the application. According to the embodiment of the application, the plate blank parameter information is input into a rolling model, and the set rolling parameter information is output through the rolling model, which concretely comprises the following steps:
s301, acquiring slab parameter information to obtain a slab thickness data set, a slab composition data set and a slab metallographic structure data set;
S302, generating data set proportion information according to weight information of slab parameters, calling slab thickness data quantity, slab component data quantity and slab metallographic structure data quantity of corresponding proportion according to the data set proportion information, and generating a training data set;
s303, inputting a training data set into a rolling model to perform model training, obtaining a training result, and judging whether the training result is converged;
s304, if the rolling model is converged, outputting set rolling parameter information according to the rolling model;
and S305, if the rolling model is not converged, adjusting the proportion of the data sets, generating a new training data set, and training the rolling model according to the new training data set until the rolling model is converged.
The method is characterized in that the proportion of the data set is continuously adjusted through the weight information of the slab parameters, so that the training effect is improved in the training process of the rolling model, and the output result of the rolling model is more close to the actual result.
According to the embodiment of the invention, the slab is rolled according to the set rolling parameter information, and the real-time rolling state information is acquired, which comprises the following steps:
acquiring rolling parameter information, wherein the rolling parameter information comprises rolling temperature, rolling speed and rolling force;
Analyzing the rolling temperature, rolling speed and rolling force of different time nodes according to the rolling parameter information;
Performing difference calculation on the rolling temperatures of adjacent time nodes to obtain temperature differences;
judging whether the temperature difference is larger than or equal to a set temperature threshold value;
If the rolling temperature is greater than or equal to the preset rolling temperature, adjusting the rolling temperature;
If the rolling state information is smaller than the current rolling temperature, rolling state information is generated according to the current rolling temperature.
It should be noted that, by analyzing the rolling temperatures of different time nodes, it is determined whether the current rolling temperature is abnormal, and the rolling temperature is dynamically adjusted according to the temperature difference, so that the rolling temperature can meet the requirements.
According to the embodiment of the invention, the rolling temperature, rolling speed and rolling force of different time nodes are analyzed according to the rolling parameter information, and the method further comprises the following steps:
Acquiring rolling speeds of different time nodes, and analyzing speed change rates according to the rolling speeds of the different time nodes;
analyzing rolling forces corresponding to different time nodes according to the speed change rate, and generating a relation curve of the rolling speed and the rolling forces;
analyzing the variation of the rolling force according to the relation curve of the rolling speed and the rolling force;
Analyzing impurity treatment results according to the variation of rolling force;
judging whether the rolling treatment result meets the requirement;
if the requirements are met, rolling the plate blank according to the current rolling speed and rolling force;
If the rolling speed or rolling force is not satisfied, the rolling speed or rolling force is adjusted.
It is to be noted that, the impurity treatment result is obtained by analyzing the rolling speed and the corresponding rolling force of different time nodes, and whether the impurity treatment result meets the requirement is judged, so that the rolling speed and the rolling force are accurately adjusted, and the impurity treatment effect is improved.
According to the embodiment of the invention, the change data of the slab parameter information is analyzed based on the real-time rolling state information, the quality evaluation model is input according to the change data of the slab parameter information, and the rolling product quality evaluation result is output according to the quality evaluation model, and the method specifically comprises the following steps:
Acquiring rolling state information of different time nodes, and comparing rolling state information of adjacent time nodes to obtain a state difference value;
calculating the parameter variation of the slab according to the state difference value, and analyzing the parameter variation of the slab according to the quality evaluation model;
If the variable quantity of the slab parameter is larger than the first variable quantity threshold value and smaller than the second variable quantity threshold value, generating first quality evaluation information;
if the variable quantity of the slab parameter is larger than or equal to a second variable quantity threshold value, generating second quality evaluation information;
generating a rolled product quality evaluation result according to the first quality evaluation information and the second quality evaluation information;
The training method of the quality evaluation model comprises the following steps:
generating training data based on the relation between the plate blank parameter change information and the quality evaluation result;
Performing iterative training on the quality evaluation model for a plurality of times according to the training data, and dynamically adjusting model parameters of the quality evaluation model according to the iterative training result;
Randomly extracting training data to establish a verification set, and inputting the verification set into a trained quality evaluation model for verification to obtain a verification result;
And adding constraint conditions to the quality evaluation model based on the verification result to obtain a final quality evaluation model, and analyzing the parameter variation of the slab based on the final quality evaluation model, wherein the constraint conditions comprise the value range of the model parameters or the number of iterative training times.
The rolling state information of different time nodes is analyzed to judge the variable quantity of the slab parameters, and different quality evaluation information is generated by different variable quantities of the slab parameters, so that the quality of a rolled product is accurately evaluated, and the evaluation precision is improved.
According to the embodiment of the invention, rolling parameter information is obtained, wherein the rolling parameter information comprises rolling temperature, rolling speed and rolling force, and the method further comprises the following steps:
obtaining rolling speed and rolling force, and obtaining a metallographic structure in a plate blank according to the rolling force;
Analyzing metallographic structure change information according to rolling force change information of different time nodes;
Analyzing slab crystal granularity change information according to metallographic structure change information;
Analyzing impurity treatment information according to the slab crystal granularity change information;
comparing the impurity treatment information with the set impurity information to obtain an impurity removal deviation rate;
judging whether the impurity removal deviation rate is greater than or equal to a set removal deviation rate threshold value;
If the rolling speed is greater than or equal to the rolling speed, adjusting the rolling force;
And if the temperature is less than the preset temperature, generating a metallographic structure of the rolled product.
In the impurity removal process, the metallographic structure change state of the slab is analyzed to obtain the impurity removal effect, so that the rolling speed and the rolling force are continuously adjusted, and the impurity removal effect is improved.
In a second aspect, an embodiment of the present application provides an impurity removal reminding system applied to slab rolling, the system including: the device comprises a memory and a processor, wherein the memory comprises a program applied to an impurity removal reminding method under slab rolling, and the program applied to the impurity removal reminding method under slab rolling realizes the following steps when being executed by the processor:
Acquiring slab parameter information, wherein the slab parameter information comprises slab thickness, slab components and slab metallographic structure;
inputting the slab parameter information into a rolling model, and outputting the set rolling parameter information through the rolling model;
Rolling the slab according to the set rolling parameter information, and acquiring real-time rolling state information;
Analyzing the change data of the slab parameter information based on the real-time rolling state information, inputting a quality evaluation model according to the change data of the slab parameter information, and outputting a rolling product quality evaluation result according to the quality evaluation model;
And generating impurity removal information according to the quality evaluation result, and transmitting the impurity removal information to a terminal for impurity removal reminding.
The rolling model is used for accurately outputting rolling parameters, so that the impurity removal effect in the slab rolling process is improved, the impurity treatment requirement is met when the quality of a rolled product is evaluated, and the impurity treatment precision is improved.
According to the embodiment of the invention, the method for acquiring the slab parameter information comprises the following steps:
Collecting slab images, extracting image features, and carrying out normalization processing on the image features to obtain optimized image features;
comparing the optimized image features with the set reference features to obtain feature deviation rates;
judging whether the characteristic deviation rate is larger than or equal to a preset characteristic deviation rate threshold value;
if the image is larger than or equal to the background feature, judging the optimized image feature as the background feature, and eliminating the background feature;
if the thickness of the slab is smaller than the preset value, judging the slab characteristics, acquiring slab edge characteristics according to the slab characteristics, and generating the thickness of the slab.
By analyzing the slab image, the background features and the slab features are accurately screened out, the slab features are independently analyzed, the slab thickness is accurately obtained, and the slab rolling effect is improved.
According to the embodiment of the invention, the plate blank parameter information is input into a rolling model, and the set rolling parameter information is output through the rolling model, which concretely comprises the following steps:
Acquiring slab parameter information to obtain a slab thickness data set, a slab composition data set and a slab metallographic structure data set;
Generating data set proportion information according to the weight information of the slab parameters, calling slab thickness data quantity, slab component data quantity and slab metallographic structure data quantity of corresponding proportion according to the data set proportion information, and generating a training data set;
inputting the training data set into a rolling model for model training to obtain a training result, and judging whether the training result is converged;
If the rolling parameters are converged, outputting the set rolling parameter information according to the rolling model;
if the rolling model is not converged, the proportion of the data set is adjusted, a new training data set is generated, and the rolling model is trained according to the new training data set until the rolling model is converged.
The method is characterized in that the proportion of the data set is continuously adjusted through the weight information of the slab parameters, so that the training effect is improved in the training process of the rolling model, and the output result of the rolling model is more close to the actual result.
According to the embodiment of the invention, the slab is rolled according to the set rolling parameter information, and the real-time rolling state information is acquired, which comprises the following steps:
acquiring rolling parameter information, wherein the rolling parameter information comprises rolling temperature, rolling speed and rolling force;
Analyzing the rolling temperature, rolling speed and rolling force of different time nodes according to the rolling parameter information;
Performing difference calculation on the rolling temperatures of adjacent time nodes to obtain temperature differences;
judging whether the temperature difference is larger than or equal to a set temperature threshold value;
If the rolling temperature is greater than or equal to the preset rolling temperature, adjusting the rolling temperature;
If the rolling state information is smaller than the current rolling temperature, rolling state information is generated according to the current rolling temperature.
It should be noted that, by analyzing the rolling temperatures of different time nodes, it is determined whether the current rolling temperature is abnormal, and the rolling temperature is dynamically adjusted according to the temperature difference, so that the rolling temperature can meet the requirements.
According to the embodiment of the invention, the rolling temperature, rolling speed and rolling force of different time nodes are analyzed according to the rolling parameter information, and the method further comprises the following steps:
Acquiring rolling speeds of different time nodes, and analyzing speed change rates according to the rolling speeds of the different time nodes;
analyzing rolling forces corresponding to different time nodes according to the speed change rate, and generating a relation curve of the rolling speed and the rolling forces;
analyzing the variation of the rolling force according to the relation curve of the rolling speed and the rolling force;
Analyzing impurity treatment results according to the variation of rolling force;
judging whether the rolling treatment result meets the requirement;
if the requirements are met, rolling the plate blank according to the current rolling speed and rolling force;
If the rolling speed or rolling force is not satisfied, the rolling speed or rolling force is adjusted.
It should be noted that, the impurity treatment results are obtained by analyzing the rolling rates and the corresponding rolling forces of different time nodes, and whether the impurity treatment results meet the requirements is judged, so that the impurity treatment effect is improved, specifically, the size of the rolling force can influence the precipitation capacity of the impurities, in a certain range (the setting range of the rolling force), the larger the rolling force is, the stronger the impurity precipitation capacity in the slab is, otherwise, the smaller the rolling force is, the worse the impurity precipitation capacity in the slab is, the impurity treatment effect is poor, and the setting range of the rolling force is set according to the material and metallographic structure of the slab.
According to the embodiment of the invention, the change data of the slab parameter information is analyzed based on the real-time rolling state information, the quality evaluation model is input according to the change data of the slab parameter information, and the rolling product quality evaluation result is output according to the quality evaluation model, and the method specifically comprises the following steps:
Acquiring rolling state information of different time nodes, and comparing rolling state information of adjacent time nodes to obtain a state difference value;
calculating the parameter variation of the slab according to the state difference value, and analyzing the parameter variation of the slab according to the quality evaluation model;
If the variable quantity of the slab parameter is larger than the first variable quantity threshold value and smaller than the second variable quantity threshold value, generating first quality evaluation information;
if the variable quantity of the slab parameter is larger than or equal to a second variable quantity threshold value, generating second quality evaluation information;
and generating a rolled product quality evaluation result according to the first quality evaluation information and the second quality evaluation information.
The rolling state information of different time nodes is analyzed to judge the variable quantity of the slab parameters, and different quality evaluation information is generated by different variable quantities of the slab parameters, so that the quality of a rolled product is accurately evaluated, and the evaluation precision is improved.
According to the embodiment of the invention, rolling parameter information is obtained, wherein the rolling parameter information comprises rolling temperature, rolling speed and rolling force, and the method further comprises the following steps:
obtaining rolling speed and rolling force, and obtaining a metallographic structure in a plate blank according to the rolling force;
Analyzing metallographic structure change information according to rolling force change information of different time nodes;
Analyzing slab crystal granularity change information according to metallographic structure change information;
Analyzing impurity treatment information according to the slab crystal granularity change information;
comparing the impurity treatment information with the set impurity information to obtain an impurity removal deviation rate;
judging whether the impurity removal deviation rate is greater than or equal to a set removal deviation rate threshold value;
If the rolling speed is greater than or equal to the rolling speed, adjusting the rolling force;
And if the temperature is less than the preset temperature, generating a metallographic structure of the rolled product.
In the impurity removal process, the metallographic structure change state of the slab is analyzed to obtain the impurity removal effect, so that the rolling speed and the rolling force are continuously adjusted, and the impurity removal effect is improved.
A third aspect of the present invention provides a computer-readable storage medium, the readable storage medium including therein an impurity removal reminding method program applied under slab rolling, the impurity removal reminding method program applied under slab rolling implementing the steps of the impurity removal reminding method applied under slab rolling as any one of the above.
The invention discloses a method, a system and a medium for reminding impurity removal under slab rolling, wherein the slab parameter information comprises slab thickness, slab components and slab metallographic structure; inputting the slab parameter information into a rolling model, and outputting the set rolling parameter information through the rolling model; rolling the slab according to the set rolling parameter information, and acquiring real-time rolling state information; analyzing the change data of the slab parameter information based on the real-time rolling state information, inputting a quality evaluation model according to the change data of the slab parameter information, and outputting a rolling product quality evaluation result according to the quality evaluation model; generating impurity removal information according to the quality evaluation result, and transmitting the impurity removal information to a terminal for impurity removal reminding; and generating rolling parameters according to different slab parameters, rolling the slab, removing impurities in the slab, judging the impurity removal effect by analyzing the quality of the rolled product after the treatment, and carrying out dynamic reminding to improve the rolling flexibility of the slab.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of units is only one logical function division, and there may be other divisions in actual implementation, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or optical disk, or the like, which can store program codes.
Or the above-described integrated units of the invention may be stored in a readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solution of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
Claims (4)
1. The impurity removal reminding method applied to slab rolling is characterized by comprising the following steps of:
Acquiring slab parameter information, wherein the slab parameter information comprises slab thickness, slab components and slab metallographic structure;
inputting the slab parameter information into a rolling model, and outputting the set rolling parameter information through the rolling model;
Rolling the slab according to the set rolling parameter information, and acquiring real-time rolling state information;
Analyzing the change data of the slab parameter information based on the real-time rolling state information, inputting a quality evaluation model according to the change data of the slab parameter information, and outputting a rolling product quality evaluation result according to the quality evaluation model;
Generating impurity removal information according to the quality evaluation result, and transmitting the impurity removal information to a terminal for impurity removal reminding;
inputting the plate blank parameter information into a rolling model, and outputting the set rolling parameter information through the rolling model, wherein the method specifically comprises the following steps of:
Acquiring slab parameter information to obtain a slab thickness data set, a slab composition data set and a slab metallographic structure data set;
Generating data set proportion information according to the weight information of the slab parameters, calling slab thickness data quantity, slab component data quantity and slab metallographic structure data quantity of corresponding proportion according to the data set proportion information, and generating a training data set;
inputting the training data set into a rolling model for model training to obtain a training result, and judging whether the training result is converged;
If the rolling parameters are converged, outputting the set rolling parameter information according to the rolling model;
If the rolling model is not converged, the proportion of the data set is adjusted, a new training data set is generated, and the rolling model is trained according to the new training data set until the rolling model is converged;
analyzing the change data of the slab parameter information based on the real-time rolling state information, inputting a quality evaluation model according to the change data of the slab parameter information, and outputting a rolling product quality evaluation result according to the quality evaluation model, wherein the method specifically comprises the following steps:
Acquiring rolling state information of different time nodes, and comparing rolling state information of adjacent time nodes to obtain a state difference value;
calculating the parameter variation of the slab according to the state difference value, and analyzing the parameter variation of the slab according to the quality evaluation model;
If the variable quantity of the slab parameter is larger than the first variable quantity threshold value and smaller than the second variable quantity threshold value, generating first quality evaluation information;
if the variable quantity of the slab parameter is larger than or equal to a second variable quantity threshold value, generating second quality evaluation information;
generating a rolled product quality evaluation result according to the first quality evaluation information and the second quality evaluation information;
The training method of the quality evaluation model comprises the following steps:
generating training data based on the relation between the plate blank parameter change information and the quality evaluation result;
Performing iterative training on the quality evaluation model for a plurality of times according to the training data, and dynamically adjusting model parameters of the quality evaluation model according to the iterative training result;
Randomly extracting training data to establish a verification set, and inputting the verification set into a trained quality evaluation model for verification to obtain a verification result;
Adding constraint conditions to the quality evaluation model based on the verification result to obtain a final quality evaluation model, and analyzing the parameter variation of the slab based on the final quality evaluation model, wherein the constraint conditions comprise the value range of the model parameters or the number of iterative training times;
the method for acquiring the slab parameter information specifically comprises the following steps:
Collecting slab images, extracting image features, and carrying out normalization processing on the image features to obtain optimized image features;
comparing the optimized image features with the set reference features to obtain feature deviation rates;
judging whether the characteristic deviation rate is larger than or equal to a preset characteristic deviation rate threshold value;
if the image is larger than or equal to the background feature, judging the optimized image feature as the background feature, and eliminating the background feature;
if the thickness of the slab is smaller than the preset value, judging the slab characteristics, acquiring slab edge characteristics according to the slab characteristics, and generating the thickness of the slab;
Rolling the slab according to the set rolling parameter information and acquiring real-time rolling state information, and specifically comprises the following steps:
acquiring rolling parameter information, wherein the rolling parameter information comprises rolling temperature, rolling speed and rolling force;
Analyzing the rolling temperature, rolling speed and rolling force of different time nodes according to the rolling parameter information;
Performing difference calculation on the rolling temperatures of adjacent time nodes to obtain temperature differences;
judging whether the temperature difference is larger than or equal to a set temperature threshold value;
If the rolling temperature is greater than or equal to the preset rolling temperature, adjusting the rolling temperature;
If the rolling state information is smaller than the current rolling temperature, rolling state information is generated according to the current rolling temperature.
2. The method for reminding impurity removal under slab rolling according to claim 1, wherein the rolling temperature, rolling speed and rolling force of different time nodes are analyzed according to rolling parameter information, further comprising:
Acquiring rolling speeds of different time nodes, and analyzing speed change rates according to the rolling speeds of the different time nodes;
analyzing rolling forces corresponding to different time nodes according to the speed change rate, and generating a relation curve of the rolling speed and the rolling forces;
analyzing the variation of the rolling force according to the relation curve of the rolling speed and the rolling force;
Analyzing impurity treatment results according to the variation of rolling force;
judging whether the rolling treatment result meets the requirement;
if the requirements are met, rolling the plate blank according to the current rolling speed and rolling force;
If the rolling speed or rolling force is not satisfied, the rolling speed or rolling force is adjusted.
3. Impurity removal reminding system applied to slab rolling, which is characterized in that the system comprises: the device comprises a memory and a processor, wherein the memory comprises a program applied to an impurity removal reminding method under slab rolling, and the program applied to the impurity removal reminding method under slab rolling realizes the following steps when being executed by the processor:
Acquiring slab parameter information, wherein the slab parameter information comprises slab thickness, slab components and slab metallographic structure;
inputting the slab parameter information into a rolling model, and outputting the set rolling parameter information through the rolling model;
Rolling the slab according to the set rolling parameter information, and acquiring real-time rolling state information;
Analyzing the change data of the slab parameter information based on the real-time rolling state information, inputting a quality evaluation model according to the change data of the slab parameter information, and outputting a rolling product quality evaluation result according to the quality evaluation model;
Generating impurity removal information according to the quality evaluation result, and transmitting the impurity removal information to a terminal for impurity removal reminding;
inputting the plate blank parameter information into a rolling model, and outputting the set rolling parameter information through the rolling model, wherein the method specifically comprises the following steps of:
Acquiring slab parameter information to obtain a slab thickness data set, a slab composition data set and a slab metallographic structure data set;
Generating data set proportion information according to the weight information of the slab parameters, calling slab thickness data quantity, slab component data quantity and slab metallographic structure data quantity of corresponding proportion according to the data set proportion information, and generating a training data set;
inputting the training data set into a rolling model for model training to obtain a training result, and judging whether the training result is converged;
If the rolling parameters are converged, outputting the set rolling parameter information according to the rolling model;
If the rolling model is not converged, the proportion of the data set is adjusted, a new training data set is generated, and the rolling model is trained according to the new training data set until the rolling model is converged;
analyzing the change data of the slab parameter information based on the real-time rolling state information, inputting a quality evaluation model according to the change data of the slab parameter information, and outputting a rolling product quality evaluation result according to the quality evaluation model, wherein the method specifically comprises the following steps:
Acquiring rolling state information of different time nodes, and comparing rolling state information of adjacent time nodes to obtain a state difference value;
calculating the parameter variation of the slab according to the state difference value, and analyzing the parameter variation of the slab according to the quality evaluation model;
If the variable quantity of the slab parameter is larger than the first variable quantity threshold value and smaller than the second variable quantity threshold value, generating first quality evaluation information;
if the variable quantity of the slab parameter is larger than or equal to a second variable quantity threshold value, generating second quality evaluation information;
generating a rolled product quality evaluation result according to the first quality evaluation information and the second quality evaluation information;
The training method of the quality evaluation model comprises the following steps:
generating training data based on the relation between the plate blank parameter change information and the quality evaluation result;
Performing iterative training on the quality evaluation model for a plurality of times according to the training data, and dynamically adjusting model parameters of the quality evaluation model according to the iterative training result;
Randomly extracting training data to establish a verification set, and inputting the verification set into a trained quality evaluation model for verification to obtain a verification result;
Adding constraint conditions to the quality evaluation model based on the verification result to obtain a final quality evaluation model, and analyzing the parameter variation of the slab based on the final quality evaluation model, wherein the constraint conditions comprise the value range of the model parameters or the number of iterative training times;
the method for acquiring the slab parameter information specifically comprises the following steps:
Collecting slab images, extracting image features, and carrying out normalization processing on the image features to obtain optimized image features;
comparing the optimized image features with the set reference features to obtain feature deviation rates;
judging whether the characteristic deviation rate is larger than or equal to a preset characteristic deviation rate threshold value;
if the image is larger than or equal to the background feature, judging the optimized image feature as the background feature, and eliminating the background feature;
if the thickness of the slab is smaller than the preset value, judging the slab characteristics, acquiring slab edge characteristics according to the slab characteristics, and generating the thickness of the slab;
Rolling the slab according to the set rolling parameter information and acquiring real-time rolling state information, and specifically comprises the following steps:
acquiring rolling parameter information, wherein the rolling parameter information comprises rolling temperature, rolling speed and rolling force;
Analyzing the rolling temperature, rolling speed and rolling force of different time nodes according to the rolling parameter information;
Performing difference calculation on the rolling temperatures of adjacent time nodes to obtain temperature differences;
judging whether the temperature difference is larger than or equal to a set temperature threshold value;
If the rolling temperature is greater than or equal to the preset rolling temperature, adjusting the rolling temperature;
If the rolling state information is smaller than the current rolling temperature, rolling state information is generated according to the current rolling temperature.
4. A computer-readable storage medium, wherein the computer-readable storage medium includes therein an impurity removal reminding method program applied under slab rolling, and the impurity removal reminding method program applied under slab rolling, when executed by a processor, implements the steps of the impurity removal reminding method applied under slab rolling according to any one of claims 1 to 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410240867.8A CN117828900B (en) | 2024-03-04 | 2024-03-04 | Impurity removal reminding method, system and medium applied to slab rolling |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410240867.8A CN117828900B (en) | 2024-03-04 | 2024-03-04 | Impurity removal reminding method, system and medium applied to slab rolling |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117828900A CN117828900A (en) | 2024-04-05 |
| CN117828900B true CN117828900B (en) | 2024-05-07 |
Family
ID=90521308
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410240867.8A Active CN117828900B (en) | 2024-03-04 | 2024-03-04 | Impurity removal reminding method, system and medium applied to slab rolling |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117828900B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102591286A (en) * | 2012-02-20 | 2012-07-18 | 宝山钢铁股份有限公司 | Online rolling plan dynamic pre-analysis and self-adjustment system and method |
| CN106040745A (en) * | 2016-06-02 | 2016-10-26 | 启东中冶润滑液压设备有限公司 | Lubrication system for hot rolling of vertical roller mill plate blank |
| CN116586441A (en) * | 2023-07-10 | 2023-08-15 | 江苏甬金金属科技有限公司 | Intelligent control method and system for metal rolling mill |
| CN116883439A (en) * | 2023-06-25 | 2023-10-13 | 北京科技大学 | Method and device for detecting slab contour with water stain on surface |
| CN117171936A (en) * | 2022-05-25 | 2023-12-05 | 宝山钢铁股份有限公司 | Slab quality prediction method for extracting real-time characteristic value of crystallizer based on defect mechanism |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102285523B1 (en) * | 2019-11-20 | 2021-08-03 | 현대제철 주식회사 | Steel sheet having high strength and high formability and method for manufacturing the same |
-
2024
- 2024-03-04 CN CN202410240867.8A patent/CN117828900B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102591286A (en) * | 2012-02-20 | 2012-07-18 | 宝山钢铁股份有限公司 | Online rolling plan dynamic pre-analysis and self-adjustment system and method |
| CN106040745A (en) * | 2016-06-02 | 2016-10-26 | 启东中冶润滑液压设备有限公司 | Lubrication system for hot rolling of vertical roller mill plate blank |
| CN117171936A (en) * | 2022-05-25 | 2023-12-05 | 宝山钢铁股份有限公司 | Slab quality prediction method for extracting real-time characteristic value of crystallizer based on defect mechanism |
| CN116883439A (en) * | 2023-06-25 | 2023-10-13 | 北京科技大学 | Method and device for detecting slab contour with water stain on surface |
| CN116586441A (en) * | 2023-07-10 | 2023-08-15 | 江苏甬金金属科技有限公司 | Intelligent control method and system for metal rolling mill |
Non-Patent Citations (1)
| Title |
|---|
| 板坯热轧计划编制的优化模型与算法;刘健;王彬;王柏琳;王宝;邹草云;刘青;;计算机集成制造***;20151231(第12期);173-180 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117828900A (en) | 2024-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106095916B (en) | Information-pushing method and device | |
| CN111191822A (en) | Steel parameter prediction method and terminal equipment | |
| CN110298858B (en) | Image clipping method and device | |
| CN112650921B (en) | Object recommendation method, device, equipment and storage medium | |
| CN113992340B (en) | User abnormal behavior identification method, device, equipment and storage medium | |
| CN112613773A (en) | User quality grading method and device based on user behaviors | |
| CN117828900B (en) | Impurity removal reminding method, system and medium applied to slab rolling | |
| CN114819085A (en) | Training method, prediction method and device of steel performance prediction model | |
| CN112131467A (en) | Data prediction method, system, medium and device | |
| CN112052915A (en) | Data training method, device, equipment and storage medium | |
| CN113609535A (en) | Side channel curve feature extraction method and device | |
| EP3879418B1 (en) | Identity verification method and device | |
| CN113127333B (en) | Data processing method and device, electronic equipment and storage medium | |
| CN110866043A (en) | Data preprocessing method and device, storage medium and terminal | |
| CN113504511B (en) | Radar signal processing and adjusting method and device, electronic equipment and storage medium | |
| CN114201696A (en) | Message pushing method and device, storage medium and computer equipment | |
| CN110309829B (en) | Online monitoring method and device for off-shelf of film and television resources and readable storage medium | |
| CN112215386A (en) | Personnel activity prediction method and device and computer readable storage medium | |
| CN106571934B (en) | A kind of worksheet processing method and apparatus based on regression analysis | |
| CN117689999B (en) | Method and system for realizing TC4 tape coiling process optimization | |
| CN111784389B (en) | Product customer number prediction method and device | |
| CN113807441B (en) | Abnormal sensor monitoring method and device in semiconductor structure preparation | |
| CN115757381A (en) | Data auditing method, device, electronic equipment and medium | |
| CN107369072A (en) | A kind of information recommendation method and device | |
| CN115512142A (en) | Image feature point extraction method and device and image matching method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |