CN112182852A - Method and device for predicting service life of crystallizer copper pipe - Google Patents
Method and device for predicting service life of crystallizer copper pipe Download PDFInfo
- Publication number
- CN112182852A CN112182852A CN202010933504.4A CN202010933504A CN112182852A CN 112182852 A CN112182852 A CN 112182852A CN 202010933504 A CN202010933504 A CN 202010933504A CN 112182852 A CN112182852 A CN 112182852A
- Authority
- CN
- China
- Prior art keywords
- copper pipe
- predicted
- data
- service life
- early warning
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B22—CASTING; POWDER METALLURGY
- B22D—CASTING OF METALS; CASTING OF OTHER SUBSTANCES BY THE SAME PROCESSES OR DEVICES
- B22D11/00—Continuous casting of metals, i.e. casting in indefinite lengths
- B22D11/04—Continuous casting of metals, i.e. casting in indefinite lengths into open-ended moulds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/04—Ageing analysis or optimisation against ageing
Abstract
The invention provides a method and a device for predicting the service life of a crystallizer copper pipe, which comprises the steps of respectively obtaining the taper data of each historical copper pipe and the copper pipe to be predicted; clustering the taper data of each historical copper pipe and the copper pipe to be predicted to obtain a cluster type; determining the category of the copper pipe to be predicted according to the clustering category; calculating different types of steel passing amount data in the category of the copper pipe to be predicted, and establishing a prediction model; acquiring an early warning threshold value of the service life end of the copper pipe to be predicted by using the prediction model; and outputting an early warning signal of the end of the service life of the copper pipe to be predicted according to the early warning threshold. The invention can realize the prediction and early warning of the service life of the crystallizer copper pipe to be used and reduce the probability of the copper pipe of stripping and corner crack.
Description
Technical Field
The invention belongs to the technical field of data processing, and particularly relates to a method and a device for predicting the service life of a crystallizer copper pipe.
Background
In the steel-making production, the continuous casting has the characteristics of high efficiency and energy saving, and the crystallizer is a very important part of a continuous casting machine, is a bottom-free copper pipe mould with forced water cooling and is called as the heart of the continuous casting machine. The crystallizer is a continuous copper casting device which receives molten steel injected from a tundish and solidifies the molten steel into a firm blank shell according to a specified section shape, is the most critical part in a continuous casting machine, and the structure, the material and the performance parameters of the crystallizer play a decisive role in the quality of a casting blank and the production capacity of a casting machine.
Disclosure of Invention
In view of the above disadvantages of the prior art, the present invention provides a method and an apparatus for predicting the service life of a crystallizer copper tube, which can timely warn the occurrence of the desquamation and corner crack of the crystallizer copper tube.
In order to achieve the above objects and other related objects, the present invention provides a method for predicting the service life of a copper tube of a crystallizer, comprising:
respectively obtaining the taper data of each historical copper pipe and the copper pipe to be predicted;
clustering the taper data of each historical copper pipe and the copper pipe to be predicted to obtain a cluster type;
determining the category of the copper pipe to be predicted according to the clustering category;
calculating different types of steel passing amount data in the category of the copper pipe to be predicted, and establishing a prediction model;
acquiring an early warning threshold value of the service life end of the copper pipe to be predicted by using the prediction model;
and outputting an early warning signal of the end of the service life of the copper pipe to be predicted according to the early warning threshold.
In an embodiment of the present invention, the obtaining of the taper data of each historical copper tube and the copper tube to be predicted respectively includes obtaining side taper data and arc taper data.
In an embodiment of the present invention, the taper data is taper data before the copper pipe is used.
In an embodiment of the present invention, the clustering each history copper tube and the taper data of the copper tube to be predicted, and obtaining the cluster type includes:
randomly selecting a plurality of samples from the obtained sample data as a center of initial clustering processing;
calculating the distance from the rest of other samples to each central point based on the Euclidean distance formula;
according to the calculated distance, dividing the rest samples into cluster categories represented by the central points closest to the rest samples;
calculating the cluster category center of each obtained new cluster, namely the mean value of all objects in the cluster category;
and repeating the steps until the central point of the cluster category is unchanged.
In an embodiment of the present invention, the calculating the flux data of different types in the category to which the copper pipe to be predicted belongs, and the establishing a prediction model includes:
and calculating the average accumulated steel passing amount data, the maximum accumulated steel passing amount data, the average accumulated steel passing amount data when the stripping occurs for the first time and the average accumulated steel passing amount data when the angular cracking occurs for the first time of the historical copper pipes in the category.
In an embodiment of the invention, the predicted accumulated passing steel amount data of the copper pipe to be predicted is one half of the sum of the average accumulated passing steel amount data and the maximum accumulated passing steel amount data;
the average accumulated steel passing amount data when the copper pipe is subjected to the stripping for the first time is an early warning threshold value of the copper pipe to be detected when the copper pipe is subjected to the stripping, and the average accumulated steel passing amount data when the copper pipe is subjected to the angular cracking for the first time is an early warning threshold value of the copper pipe to be detected when the copper pipe is subjected to the angular cracking.
In an embodiment of the present invention, outputting the early warning signal of the end of the service life of the copper pipe to be predicted according to the early warning threshold includes:
and displaying the early warning signal to a user through a display interface, wherein the display interface comprises a copper pipe taper analysis interface and a copper pipe state monitoring interface.
In an embodiment of the invention, the copper pipe state monitoring interface displays different colors to indicate the early warning degree.
A crystallizer copper pipe service life prediction device is characterized by comprising:
a data memory and a processor;
the data memory is used for acquiring and storing the taper data of each historical copper pipe and the copper pipe to be predicted;
the processor is connected with the data memory and is used for clustering the taper data of each historical copper pipe and the copper pipe to be predicted to obtain a cluster type; determining the category of the copper pipe to be predicted according to the clustering category; calculating different types of steel passing amount data in the category of the copper pipe to be predicted, and establishing a prediction model; acquiring an early warning threshold value of the service life end of the copper pipe to be predicted by using the prediction model; and outputting the early warning signal of the service life ending of the copper pipe to be predicted.
The invention discloses a method and a device for predicting the service life of a crystallizer copper pipe. And then, calculating accumulated steel passing amount data of the historical copper pipe to obtain an early warning threshold value of the service life of the copper pipe to be predicted, and sending an early warning signal. The technical scheme of the invention can effectively carry out early warning on the occurrence of the stripping and corner cracking of the crystallizer copper tube in the production process, and reduce the exceeding rate of the stripping and corner cracking.
Of course, it is not necessary for any product in which the invention is practiced to achieve all of the above-described advantages at the same time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart illustrating a method for predicting the service life of a copper tube of a crystallizer according to an embodiment of the present invention;
fig. 2 is a schematic view illustrating an arc structure of a copper tube of a crystallizer according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a clustering algorithm of a method for predicting the service life of a copper tube of a crystallizer according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram illustrating a device for predicting the service life of a copper tube of a crystallizer according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The thickness of four solidified blank shells in a copper pipe of the crystallizer is inconsistent due to the influence of the factors of cooling, non-uniform flow field or peritectic phase change of metal on the solidification shrinkage of a primary blank shell of a continuous casting billet on each surface of molten steel in the crystallizer. The blank shell at the local position is well contacted with the copper pipe, and the blank shells at other areas are separated from the wall of the copper pipe to generate air gaps, so that a stripping square is formed. The corner with stronger cooling of the casting blank forms an acute angle, and the corner with weaker cooling forms an obtuse angle. If the casting blank is unevenly cooled or poorly clamped on each surface of the secondary cooling area, the shrinkage of the blank shell is worse, and the degree of stripping is aggravated or even exceeds the standard. Meanwhile, when the steel feeding amount of the crystallizer reaches a certain degree, the stripping or corner cracking is easy to occur. There are two key factors that cause the casting blank to come off square and the corner cracks: the taper design of the copper pipe and the accumulated flux value in the using process. The prediction method provided by the invention can realize monitoring of the state of the copper pipe and achieve the purpose of early warning the copper pipe against the square deviation and the angular crack.
Referring to fig. 1, the method for predicting the service life of a copper tube of a crystallizer provided by the present invention includes:
and S101, respectively obtaining the taper data of each historical copper pipe and the copper pipe to be predicted.
It should be noted that the copper tube of the crystallizer may be a square or rectangular copper tube bent to one side, the inner cavity of the copper tube is tapered from the upper opening to the lower opening, and the inner cavity of the copper tube is tapered segments from the upper opening to the lower opening, such as a double cone, a triple cone, a multi-cone, and the like. Taper refers to the amount of change in two cross-sectional dimensions of the inner surface of the copper tube over a length. The taper data can refer to side taper data and/or cambered surface taper data of each historical copper pipe and copper pipe to be predicted, and the side taper data and the cambered surface taper data can be obtained through measurement of a taper detector. The side taper data and the cambered surface taper data are taper data of each copper pipe before use, and managers measure, record and upload the data to a database. Because the taper data of the copper pipe can not be monitored in the using process of the crystallizer copper pipe, the prediction method provided by the invention is used for carrying out comparative analysis on the taper data of all the copper pipes before use.
Referring to fig. 2, in an embodiment of the present invention, the taper data may be, for example, an inner diameter width of a copper pipe, the inner diameter width of the copper pipe may be a side inner diameter width and/or an arc inner diameter width, the side inner diameter width refers to a distance between side surfaces at two ends of the copper pipe, and the arc inner diameter width refers to a distance between two points of an arc section of the copper pipe. The arc-shaped section of the copper pipe may include a first arc-shaped surface and a second arc-shaped surface, the first arc-shaped surface is located inside the copper pipe, the second arc-shaped surface is located outside the copper pipe, for example, the first arc-shaped surface has a width of X1, and the second arc-shaped surface has a width of X2. In the actual production process, along with the continuous increase of logical steel volume data, the copper pipe can take place deformation, and when the deformation of copper pipe reached the certain degree, the tapering of copper pipe changed, appears taking off the side easily. However, the range of the change in the taper is very subtle, and it is difficult to intuitively explain the problem. Because the crystallizer copper pipe is a square or rectangular copper pipe bent towards one side, the deformation of the copper pipe at the arc part is obvious, and the subsequent data analysis and prediction are facilitated.
And S102, clustering the taper data of each historical copper pipe and the copper pipe to be predicted to obtain a cluster type.
The number of the cluster categories may be multiple, and the cluster categories may be classified by a partition method, for example, the cluster processing may be performed by using a K-means algorithm, and the cluster processing is performed on the taper data of each historical copper pipe and the copper pipe to be predicted, so as to obtain the cluster categories.
Referring to fig. 3, the K-means algorithm clustering process can be implemented by the following steps:
s201: and randomly selecting a plurality of samples from the acquired sample data as the center of the initial clustering process. It will be appreciated that the steps may construct a plurality of groups, each group representing a cluster.
S202: the distance of the remaining other samples to each center point is calculated based on the euclidean distance formula.
S203: and according to the calculated distance, dividing the rest samples into cluster categories represented by the central points closest to the rest samples.
S204: the cluster class center of each obtained new cluster, i.e., the mean of all objects in the cluster class, is calculated.
S205: steps S202 to S204 are repeated until the center point of the cluster category is unchanged.
It should be noted that the objects in the same cluster are as close to or related to each other as possible, and the objects in different clusters are as far from or different from each other as possible, so as to achieve a distinguishing purpose.
S103, determining the category of the copper pipe to be predicted according to the clustering category.
It should be noted that the taper data of the copper tubes are already classified into different categories by the clustering algorithm, that is, the data of the copper tubes to be predicted are included in a certain clustering category.
And S104, calculating different types of steel passing amount data in the class of the copper pipe to be predicted, and establishing a prediction model.
It should be noted that the steel passing amount data is an important index reflecting the service life level of the copper pipe of the crystallizer, and the steel passing amount data of the historical copper pipe is recorded and uploaded to the database in the use process. The different types of steel passing amount data are respectively in the category, except the data of the copper pipe to be predicted, the average accumulated steel passing amount data t of other copper pipe data1Data t of maximum cumulative steel passing amount2Average accumulated steel flux data t when the first slip occurs3Average cumulative flux data t at first incidence of angular cracking4。
And S105, acquiring an early warning threshold value of the service life ending of the copper pipe to be predicted by using the prediction model.
It should be noted that the data of the predicted accumulated steel passing amount of the copper pipe to be predicted is the service life of the copper pipe. The predicted accumulated steel passing amount data t' of the copper pipe to be predicted is the average accumulated steel passing amount data t1And the maximum accumulated steel passing amount data t2One half of the sum, i.e. t' ═ t1+t2)/2. The average accumulated steel passing amount data t when the stripping occurs for the first time3The average accumulated steel passing amount data t when the angular crack occurs for the early warning threshold value of the copper pipe to be detected4The early warning threshold value is the early warning threshold value when the copper pipe to be detected has angular crack.
S106: and outputting an early warning signal of the end of the service life of the copper pipe to be predicted according to the early warning threshold.
It should be noted that the early warning signal is displayed to the user through a display interface, the display interface may include a copper pipe taper analysis interface and a copper pipe state monitoring interface, and the taper analysis interface may display taper data of different copper pipes before use and may perform an analogy. The copper pipe state monitoring interface displays different colors to represent the state of the copper pipe, for example, assuming that the predicted accumulated passing steel amount data of the copper pipe is ten thousand tons, when the remaining bearable passing steel amount data of the copper pipe is 100% -70%, for example, the copper pipe state monitoring interface displays a green signal, when the remaining bearable passing steel amount data of the copper pipe is 70% -30%, for example, the copper pipe state monitoring interface displays a yellow signal, and when the remaining bearable passing steel amount data of the copper pipe is lower than 30%, for example, the copper pipe state interface displays a red signal. When the copper pipe state interface displays a red signal, further, the early warning signal can be displayed according to the early warning threshold value obtained in the step S105, for example, a light early warning can display a light pink signal, a moderate early warning can display a red signal, and a severe early warning can display a deep red signal. The user can in time change the copper pipe or take remedial action etc. according to the early warning signal of difference, reduces the probability that the copper pipe appears taking off and puts and the angular crack.
Referring to fig. 1 to 3, in an embodiment of the present invention, the continuous casting machine may be, for example, 4 zones with 8 streams, each having a stopper rod, a fixed diameter nozzle with a quick-change structure, and a submerged nozzle protecting a sleeve for casting mold flux; the tubular crystallizer is provided with an external electromagnetic stirrer. The length of the copper tube of the crystallizer may be 900mm, for example, the material may be a metal material, for example, a copper-silver chrome plating, and the wall thickness may be 15mm, for example. Selecting taper data before use of a plurality of copper pipes produced by different manufacturers as samples, wherein the taper data can be 78 copper pipes, for example, the copper pipes comprise a new copper pipe (to-be-predicted copper pipe), the taper sample data are sequentially arranged from small to large, the data arranged in the first 30 (including the 30 th) are amplified, for example, the amplification can be 1.1 times, and the amplified data and other data which are not amplified are clustered by adopting a K-means algorithm, for example, 3 categories can be obtained. Determining the category of the new online copper pipe, for example, the category may be category a, and calculating the data of the steel passing amount of the copper pipes except the new online copper pipe in category a: average accumulated steel passing amount data t1Data t of maximum cumulative steel passing amount2Average accumulated steel flux data t when the first slip occurs3Average cumulative flux data t at first incidence of angular cracking4. The accumulated steel passing amount data of the historical copper pipe can be obtained by consulting the use record of the crystallizer. The predicted accumulated steel passing amount data t' of the new online copper pipe is the average accumulated steel passing amount data t1And the placeThe maximum accumulated steel passing amount data t2One half of the sum, i.e. t' ═ t1+t2)/2. The average accumulated steel passing amount data t when the stripping occurs for the first time3The accumulated steel passing amount data t when the angle crack occurs for the first time is averaged to be the early warning threshold value of the new on-line copper pipe for the occurrence of the stripping4And the early warning threshold value is the early warning threshold value when the new on-line copper pipe has angular crack. According to the prediction method, the historical copper pipe most similar to the new online copper pipe is selected for comparison through cluster analysis of the taper data of the historical copper pipe and the taper data of the new online copper pipe before use, the steel passing amount data of all the historical copper pipes are summarized, and the service life of the new copper pipe and the early warning threshold values of the new copper pipe with the stripping and the angular cracking are deduced.
Referring to fig. 4, a device 300 for predicting the service life of a copper tube of a crystallizer includes:
a data memory 301 and a processor 302;
the data memory 301 is used for acquiring and storing taper data of each historical copper pipe and copper pipe to be predicted;
the processor 302 is connected to the data storage 301, and is configured to perform clustering processing on the taper data of each history copper pipe and the copper pipe to be predicted, so as to obtain a cluster type; determining the category of the copper pipe to be predicted according to the clustering category; calculating different types of steel passing amount data in the category of the copper pipe to be predicted, and establishing a prediction model; acquiring an early warning threshold value of the service life end of the copper pipe to be predicted by using the prediction model; and outputting the early warning signal of the service life ending of the copper pipe to be predicted.
For example, the data storage 301 may be a PostgreSQL database system, and may record and store data, where the taper data may include side taper data and cambered surface taper data.
For example, the clustering process may adopt a K-means clustering algorithm, and the K-means clustering algorithm process may be implemented by the following steps:
s201: and randomly selecting a plurality of samples from the acquired sample data as the center of the initial clustering process. It will be appreciated that the steps may construct a plurality of groups, each group representing a cluster.
S202: the distance of the remaining other samples to each center point is calculated based on the euclidean distance formula.
S203: and according to the calculated distance, dividing the rest samples into cluster categories represented by the central points closest to the rest samples.
S204: the cluster class center of each obtained new cluster, i.e., the mean of all objects in the cluster class, is calculated.
S205: steps S202 to S204 are repeated until the center point of the cluster category is unchanged.
It should be noted that the objects in the same cluster category obtained finally are as close to or related to each other as possible, and the objects in different clusters are as far away from or different as possible, so as to achieve a distinguishing purpose.
For example, the processor 302 may find, by a program, in which cluster class the taper data of the copper pipe to be predicted is included, and determine the taper data of all copper pipes included in the cluster class. And determining the number of the corresponding copper pipe according to the taper data.
For example, the passing steel amount data can comprise average accumulated passing steel amount data t1Data t of maximum cumulative steel passing amount2Average accumulated steel flux data t when the first slip occurs3Average cumulative flux data t at first incidence of angular cracking4. The accumulated steel passing amount data of the historical copper pipes can be obtained from the use records of the copper pipes, and the steel passing amount data of each copper pipe is recorded in the use process.
For example, the data of the predicted accumulated steel passing amount of the copper pipe to be predicted is the service life of the copper pipe. The predicted accumulated steel passing amount data t' of the new online copper pipe is the average accumulated steel passing amount data t1And the maximum accumulated steel passing amount data t2One half of the sum, i.e. t' ═ t1+t2)/2. The average accumulated steel passing amount data t when the stripping occurs for the first time3Copper tube for the new lineThe early warning threshold value of the slip-generating party, the average accumulated steel passing amount data t when the angular crack occurs for the first time4And the early warning threshold value is the early warning threshold value when the new on-line copper pipe has angular crack.
For example, the warning signal may indicate the status of the copper tube by displaying different colors. For example, assuming that the predicted accumulated passing steel amount data of the copper pipe is ten thousand tons, when the remaining acceptable passing steel amount data of the copper pipe is, for example, 100% -70%, the copper pipe state monitoring interface displays a green signal, when the remaining acceptable passing steel amount data of the copper pipe is, for example, 70% -30%, the copper pipe state monitoring interface displays a yellow signal, and when the remaining acceptable passing steel amount data of the copper pipe is, for example, less than 30%, the copper pipe state interface displays a red signal. When the copper pipe state interface displays a red signal, further, an early warning signal can be displayed according to the early warning threshold value, for example, a light early warning can display a light pink signal, a moderate early warning can display a red signal, and a severe early warning can display a deep red signal. The user can in time change the copper pipe or take remedial action etc. according to the early warning signal of difference, reduces the probability that the copper pipe appears taking off and puts and the angular crack.
The working principle of the relevant units of the crystallizer copper tube service life prediction device provided by the embodiment of the invention can be referred to the embodiment part of the method, and the description is not repeated here.
In summary, the invention provides a method and a device for predicting the service life of a crystallizer copper pipe, which are used for determining the category of the copper pipe to be predicted by clustering the measured taper data of each crystallizer copper pipe, calculating the steel passing amount data of other copper pipes except the copper pipe to be predicted in the category, and obtaining the early warning threshold value of the copper pipe to be predicted for the occurrence of square off and angular cracking. The invention gives early warning to the casting blank to be stripped and the corner crack based on the taper of the copper pipe, and finds and solves the production quality problem possibly occurring in the production process as early as possible.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (9)
1. A prediction method for the service life of a crystallizer copper pipe is characterized by comprising the following steps:
respectively obtaining the taper data of each historical copper pipe and the copper pipe to be predicted;
clustering the taper data of each historical copper pipe and the copper pipe to be predicted to obtain a cluster type;
determining the category of the copper pipe to be predicted according to the clustering category;
calculating different types of steel passing amount data in the category of the copper pipe to be predicted, and establishing a prediction model;
acquiring an early warning threshold value of the service life end of the copper pipe to be predicted by using the prediction model;
and outputting an early warning signal of the end of the service life of the copper pipe to be predicted according to the early warning threshold.
2. The method for predicting the service life of the copper tube of the crystallizer according to claim 1, wherein the step of respectively obtaining the taper data of each historical copper tube and the copper tube to be predicted comprises the step of obtaining side taper data and cambered surface taper data.
3. A method for predicting the service life of a crystallizer copper tube as claimed in claim 1 or 2, wherein said conicity data is conicity data of the copper tube before use.
4. The method for predicting the service life of the copper tube of the crystallizer according to claim 1, wherein the step of clustering the taper data of each historical copper tube and the copper tube to be predicted to obtain the cluster type comprises the following steps:
randomly selecting a plurality of samples from the obtained sample data as a center of initial clustering processing;
calculating the distance from the rest of other samples to each central point based on the Euclidean distance formula;
according to the calculated distance, dividing the rest samples into cluster categories represented by the central points closest to the rest samples;
calculating the cluster category center of each obtained new cluster, namely the mean value of all objects in the cluster category;
and repeating the steps until the central point of the cluster category is unchanged.
5. The method for predicting the service life of the copper pipe of the crystallizer according to claim 1, wherein the step of calculating the steel passing amount data of different types in the category of the copper pipe to be predicted comprises the following steps:
and calculating the average accumulated steel passing amount data, the maximum accumulated steel passing amount data, the average accumulated steel passing amount data when the stripping occurs for the first time and the average accumulated steel passing amount data when the angular cracking occurs for the first time of the historical copper pipes in the category.
6. The method for predicting the service life of the copper pipe of the crystallizer as recited in claim 5, wherein the predicted accumulated passing steel amount data of the copper pipe to be predicted is half of the sum of the average accumulated passing steel amount data and the maximum accumulated passing steel amount data;
the average accumulated steel passing amount data when the copper pipe is subjected to the stripping for the first time is an early warning threshold value of the copper pipe to be detected when the copper pipe is subjected to the stripping, and the average accumulated steel passing amount data when the copper pipe is subjected to the angular cracking for the first time is an early warning threshold value of the copper pipe to be detected when the copper pipe is subjected to the angular cracking.
7. The method for predicting the service life of the copper pipe of the crystallizer according to claim 1, wherein outputting the early warning signal of the service life end of the copper pipe to be predicted according to the early warning threshold comprises:
and displaying the early warning signal to a user through a display interface, wherein the display interface comprises a copper pipe taper analysis interface and a copper pipe state monitoring interface.
8. The method for predicting the service life of the copper pipe of the crystallizer as claimed in claim 7, wherein the state monitoring interface of the copper pipe shows the early warning degree by displaying different colors.
9. A crystallizer copper pipe service life prediction device is characterized by comprising:
a data memory and a processor;
the data memory is used for acquiring and storing the taper data of each historical copper pipe and the copper pipe to be predicted;
the processor is connected with the data memory and is used for clustering the taper data of each historical copper pipe and the copper pipe to be predicted to obtain a cluster type; determining the category of the copper pipe to be predicted according to the clustering category; calculating different types of steel passing amount data in the category of the copper pipe to be predicted, and establishing a prediction model; acquiring an early warning threshold value of the service life end of the copper pipe to be predicted by using the prediction model; and outputting the early warning signal of the service life ending of the copper pipe to be predicted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010933504.4A CN112182852A (en) | 2020-09-08 | 2020-09-08 | Method and device for predicting service life of crystallizer copper pipe |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010933504.4A CN112182852A (en) | 2020-09-08 | 2020-09-08 | Method and device for predicting service life of crystallizer copper pipe |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112182852A true CN112182852A (en) | 2021-01-05 |
Family
ID=73924900
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010933504.4A Pending CN112182852A (en) | 2020-09-08 | 2020-09-08 | Method and device for predicting service life of crystallizer copper pipe |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112182852A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105740625A (en) * | 2016-01-31 | 2016-07-06 | 太原科技大学 | Real time residual life prediction method of gear |
| CN105929812A (en) * | 2016-04-18 | 2016-09-07 | 北京科技大学 | Strip steel hot continuous rolling quality fault diagnosis method and device |
| CN106238695A (en) * | 2016-08-12 | 2016-12-21 | 湖南千盟物联信息技术有限公司 | Casting stream solidification forecast Control Algorithm in a kind of casting process crystallizer |
| CN108921232A (en) * | 2018-07-31 | 2018-11-30 | 东北大学 | A kind of hot-strip Cooling History data clusters and method for measuring similarity |
| CN109530648A (en) * | 2019-01-28 | 2019-03-29 | 东北大学 | A kind of method of crystallizer slag interface fluctuation in prediction continuous casting |
| CN110153390A (en) * | 2019-06-10 | 2019-08-23 | 成渝钒钛科技有限公司 | It makes steel crystallizer steel -passing amount and deepens steel index control method |
-
2020
- 2020-09-08 CN CN202010933504.4A patent/CN112182852A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105740625A (en) * | 2016-01-31 | 2016-07-06 | 太原科技大学 | Real time residual life prediction method of gear |
| CN105929812A (en) * | 2016-04-18 | 2016-09-07 | 北京科技大学 | Strip steel hot continuous rolling quality fault diagnosis method and device |
| CN106238695A (en) * | 2016-08-12 | 2016-12-21 | 湖南千盟物联信息技术有限公司 | Casting stream solidification forecast Control Algorithm in a kind of casting process crystallizer |
| CN108921232A (en) * | 2018-07-31 | 2018-11-30 | 东北大学 | A kind of hot-strip Cooling History data clusters and method for measuring similarity |
| CN109530648A (en) * | 2019-01-28 | 2019-03-29 | 东北大学 | A kind of method of crystallizer slag interface fluctuation in prediction continuous casting |
| CN110153390A (en) * | 2019-06-10 | 2019-08-23 | 成渝钒钛科技有限公司 | It makes steel crystallizer steel -passing amount and deepens steel index control method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108705058B (en) | A method of forecast Crystallizer bleed-out is clustered based on K-Means | |
| KR102182325B1 (en) | Methods and systems for quantitative measurement of internal defects in cast steel products | |
| CN104923761B (en) | Die casting for may be cast as performance evaluation | |
| CN102151814B (en) | Bonding alarm method and system during continuous casting production | |
| CN102019393B (en) | Casting body quality judging method and device for continuous casting machine | |
| JP6358215B2 (en) | Method and apparatus for determining surface defects of continuous cast slab, and method for manufacturing steel slab using the surface defect determination method | |
| JPWO2015115651A1 (en) | Method, apparatus and program for determining casting state in continuous casting | |
| CN112182852A (en) | Method and device for predicting service life of crystallizer copper pipe | |
| CN107357953A (en) | A kind of method that nozzle blocking is analyzed according to heat flow density | |
| CN114012053B (en) | Method for judging abnormal state of crystallizer immersed nozzle nodulation and blockage | |
| TWI762264B (en) | Method for predicting temperature of molten steel | |
| CN107498027A (en) | Large ship rises liquid method with the automatic cut-off of copper alloy propeller antigravity casting | |
| JP6390718B2 (en) | Continuously cast slab, manufacturing method and manufacturing apparatus thereof, manufacturing method and manufacturing apparatus of thick steel plate | |
| CN111579592B (en) | Method for monitoring corrosion degree of high-temperature operation container | |
| EP3202508A1 (en) | Feeding device and system and high pressure moulding method | |
| CN110918973B (en) | Crystallizer thermal image abnormal region marking method based on run | |
| CN111506030A (en) | Quality management system and method for automobile production line | |
| CN115797361A (en) | Aluminum template surface defect detection method | |
| CN1325196C (en) | Continuous casting mold for casting molten metals, particularly steel materials, at high casting rates to form polygonal billet, bloom, and preliminary section castings and the like | |
| JP6347236B2 (en) | Breakout prediction method, breakout prediction apparatus, and continuous casting method | |
| CN108097905A (en) | A kind of bleed-out method for early warning | |
| CN116611029B (en) | Method and device for generating parameter data set in continuous casting production process of whole casting time | |
| JPH01228658A (en) | Method for predicting longitudinal crack in continuous casting | |
| CN214108718U (en) | Visual adjustable synchronous cooling crystallizer | |
| JP5943402B1 (en) | Measuring apparatus, method, computer program and computer-readable recording medium for quantifying casting defects |
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 |