CN114781110B - Hot rolled coil plate warping defect tracing method and system based on data analysis - Google Patents
Hot rolled coil plate warping defect tracing method and system based on data analysis Download PDFInfo
- Publication number
- CN114781110B CN114781110B CN202210178234.XA CN202210178234A CN114781110B CN 114781110 B CN114781110 B CN 114781110B CN 202210178234 A CN202210178234 A CN 202210178234A CN 114781110 B CN114781110 B CN 114781110B
- Authority
- CN
- China
- Prior art keywords
- skin
- defect
- lifting
- production
- heat
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 158
- 238000000034 method Methods 0.000 title claims abstract description 95
- 238000007405 data analysis Methods 0.000 title claims abstract description 19
- 238000004519 manufacturing process Methods 0.000 claims abstract description 123
- 230000008569 process Effects 0.000 claims description 72
- 238000005266 casting Methods 0.000 claims description 39
- 229910000831 Steel Inorganic materials 0.000 claims description 27
- 239000010959 steel Substances 0.000 claims description 27
- 239000007788 liquid Substances 0.000 claims description 20
- 238000009749 continuous casting Methods 0.000 claims description 8
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 7
- 238000007664 blowing Methods 0.000 claims description 7
- 229910052760 oxygen Inorganic materials 0.000 claims description 7
- 239000001301 oxygen Substances 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000009489 vacuum treatment Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 4
- 238000003723 Smelting Methods 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000005452 bending Methods 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 6
- 230000006872 improvement Effects 0.000 description 4
- 238000010079 rubber tapping Methods 0.000 description 3
- 230000002950 deficient Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000011112 process operation Methods 0.000 description 1
- 238000009628 steelmaking Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- General Factory Administration (AREA)
Abstract
The invention discloses a hot rolled coil plate warping defect tracing method and system based on data analysis, and relates to the technical field of hot rolled coil plate production. According to the technical scheme, real-time production data of workshops are utilized, main influencing technological parameters of the existing skin-lifting defects are accurately and reliably analyzed, the contribution of each furnace and each type of furnace to the existing skin-lifting defect rate is quantitatively calculated, and therefore the skin-lifting defect rate is effectively reduced, and the overall quality and the production benefit of produced products are improved.
Description
Technical Field
The invention relates to the technical field of hot-rolled coil production, in particular to a hot-rolled coil warping defect tracing method and system based on data analysis.
Background
The skin-tilting defect is a common surface quality defect of a hot rolled coil product. The quality detection of the product aiming at the defect, the treatment of the defective product, the interference on the production organization scheduling caused by the treatment of the defective product and the like bring high cost to workshop production. Because of the direct and indirect factors causing the defects, the involved process flow is longer, the specific process links and corresponding process parameters causing the skin-lifting defects are difficult to determine for the specific workshop production process, and great difficulty is brought to the effective pressure drop skin-lifting defect rate.
At present, aiming at the specific production process flow of a specific workshop, no effective method exists in judging the exact cause of the skin-lifting defect, workshop technicians can estimate and guess possible causes only through experience, but reliable quantitative result feedback is difficult to obtain for the change of the local operation process due to the randomness of the occurrence of the defect and the continuity of the production process; conventional process data analysis methods have many limitations in terms of the size and systematicness of the data volume, in terms of the dynamics of the analysis, and in terms of the discrimination of the production patterns of the product.
Disclosure of Invention
The invention aims to provide a hot rolled coil plate warping defect tracing method based on data analysis, which aims to solve the problems in the prior art.
In order to achieve the above purpose, the present invention provides the following technical solutions:
the hot rolled coil plate skin-lifting defect tracing method based on data analysis is used for obtaining defect types corresponding to different skin-lifting defects according to production data information of the skin-lifting defects in the process of producing the hot rolled coil plate, further obtaining influence factors of the skin-lifting defects and occurrence positions of the skin-lifting defects, collecting and obtaining historical production data information of the hot rolled coil plate produced in a specified historical period, dividing the historical production data information into production subperiods according to a preset specified historical period, and executing the following steps according to the production subperiods respectively:
step A, extracting each preset appointed type of historical process data set contained in a production subperiod based on historical production data information, preprocessing the extracted historical process data set, determining a production stage corresponding to the production subperiod based on the preprocessed historical process data set by combining a preset corresponding relation between the production stage and a production heat, and then entering step B;
b, respectively aiming at each production stage, extracting each preset characteristic value of the corresponding historical process data set based on the production stage corresponding to the production sub-period obtained in the step A to form a characteristic vector value corresponding to each preset characteristic value in the historical process data set, combining each characteristic vector value corresponding to the historical process data set corresponding to the production stage to obtain a production heat set for generating the skin-lifting defect, further obtaining each skin-lifting defect type generated in the production stage, and then entering the step C;
step C, calculating and obtaining the skin-lifting defect rate corresponding to the skin-lifting defect type corresponding to the production stage based on a production heat collection of the skin-lifting defect generated by the skin-lifting defect type, namely obtaining the skin-lifting defect rate corresponding to the skin-lifting defect type corresponding to the production stage, and then entering the step D;
step D, respectively aiming at different types of skin-lifting defects generated in the production stage, determining pouring heat when the skin-lifting defects are generated according to the skin-lifting defect rates respectively corresponding to the skin-lifting defect types in the production stage, combining characteristic vector values in historical process data sets corresponding to the skin-lifting defects under different pouring heat to obtain influencing factors for generating the skin-lifting defects, and combining the pouring heat to determine the generation positions of the skin-lifting defects.
Further, in the step a, preprocessing is performed on each history process data set of a preset designated type, the complete value in the process data is extracted, the abnormal value is removed, and the history process data set of the preset designated type comprises heat data, quality detection data, parameter data, steel grade data and interface data corresponding to the production subperiod;
the production stage comprises a converter smelting stage, a vacuum treatment stage and a continuous casting stage.
Further, in the step B, based on the production stage and the preset correspondence between the production stage and the production heat, the production heat includes a casting start furnace, a submerged nozzle replacement furnace, and a normal casting furnace, and whether the casting heat is the casting start furnace is determined according to the timestamp of the production heat and the recorded count value of the casting record;
judging whether the pouring heat is a submerged nozzle replacing furnace according to the blank pulling speed and the pouring duration time.
Further, under the same casting heat, judging whether the casting heat is a casting start furnace according to the recorded data value of the casting record, and when the count value of the casting record is zero, and the timestamp is the earliest under the same heat number, the casting start furnace is started;
judging whether the pouring heat is a submerged nozzle replacing furnace or not, and determining that the pouring heat is the submerged nozzle replacing furnace when the blank pulling speed is reduced to a preset threshold value and the casting duration time is within a preset time range.
Further, in the step B, the skin-lifting defect type includes a liquid level fluctuation defect and a process parameter quantity defect, wherein the process parameter quantity includes an oxygen blowing quantity, a minimum molten steel temperature of the tundish and a minimum molten steel weight of the tundish.
Further, aiming at different skin-tilting defect types, determining the defect as a liquid level fluctuation defect when the liquid level fluctuation of molten steel in the pouring process is larger than a preset fluctuation threshold value;
and calculating an average defect value of the process parameter based on each preset characteristic value of the historical process data set according to the skin warping defect corresponding to each process parameter, and determining the average defect value as the process parameter defect when the average defect value is larger than a preset threshold value.
The second aspect of the invention provides a hot rolled coil bending defect tracing system based on data analysis, which comprises the following steps:
the module is used for extracting each historical process data set of preset designated types contained in the production subperiod, preprocessing the extracted historical process data sets and determining the production stage corresponding to the production subperiod by combining the preset corresponding relation between the production stage and the production heat;
the module is used for respectively extracting each preset characteristic value of the corresponding historical process data set aiming at each production stage to form a characteristic vector value corresponding to each preset characteristic value in the historical process data set, and combining each characteristic vector value corresponding to the historical process data set corresponding to the production stage to obtain a production heat set for generating the skin warping defect;
the module is used for obtaining the corresponding skin-lifting defect rate of each skin-lifting defect type in the production stage;
and the module is used for respectively aiming at different types of skin-lifting defects generated in the production stage, determining pouring heat when the skin-lifting defects are generated according to the skin-lifting defect rates respectively corresponding to the skin-lifting defect types in the production stage, combining all characteristic vector values in historical process data sets corresponding to the skin-lifting defects under different pouring heat to obtain influencing factors for generating the skin-lifting defects, and combining the pouring heat to determine the generation positions of the skin-lifting defects.
A third aspect of the present invention proposes a computer readable medium storing software comprising instructions executable by one or more computers, which instructions, when executed by the one or more computers, perform the hot rolled sheet skin-lifting defect tracing method based on data analysis.
Compared with the prior art, the hot rolled coil plate warping defect tracing method based on data analysis has the following technical effects:
according to the technical scheme provided by the invention, the main influencing technological parameters of the current skin-tilting defect can be accurately and reliably analyzed by using real-time production data of a workshop, and the contribution of each heat and each type of heat to the current skin-tilting defect rate is quantitatively calculated, so that a direct and reliable reference basis is provided for on-site production on how to properly control the liquid level height of the molten steel of the crystallizer, the service life of the immersed long nozzle, the lowest liquid steel temperature of the tundish, the minimum liquid steel weight of the tundish, the steel-making tapping temperature of the converter, the oxygen blowing amount of RH vacuum treatment, the operation of opening the pouring furnace to pour and replace the immersed long nozzle and the like, and finally, the purposes of effectively reducing the skin-tilting defect rate and improving the overall quality and the production benefit of the produced product are achieved.
Drawings
Fig. 1 is a schematic flow chart of a hot rolled coil bending defect tracing method according to an exemplary embodiment of the invention.
Detailed Description
For a better understanding of the technical content of the present invention, specific examples are set forth below, along with the accompanying drawings.
Aspects of the invention are described herein with reference to the drawings, in which there are shown many illustrative embodiments. Embodiments of the present invention are not limited to those shown in the drawings. It is to be understood that this invention is capable of being carried out by any of the various concepts and embodiments described above and as such described in detail below, since the disclosed concepts and embodiments are not limited to any implementation. Additionally, some aspects of the disclosure may be used alone or in any suitable combination with other aspects of the disclosure.
Referring to fig. 1, a method for tracing a skin-lifting defect of a hot rolled coil based on data analysis is used for obtaining defect types corresponding to different skin-lifting defects according to production data information of the skin-lifting defects in the process of producing the hot rolled coil, further obtaining influencing factors of the skin-lifting defects and occurrence positions of the skin-lifting defects, collecting and obtaining historical production data information of producing the hot rolled coil in a specified historical period, wherein the historical production data information is derived from data information collected in real time in the production process stored in a database, is divided into production subperiods according to preset specified historical periods, and performs the following steps for each production subperiod respectively:
and A, extracting a historical process data set of each preset designated type contained in a production subperiod based on historical production data information, preprocessing the extracted historical process data set, extracting a complete value in the process data, removing an abnormal value, wherein the historical process data set of the preset designated type comprises heat data, quality detection data, parameter data, steel grade data and interface data corresponding to the production subperiod, determining a production stage corresponding to the production subperiod based on the preprocessed historical process data set by combining a preset corresponding relation of the production stage and a production heat, wherein the production stage comprises a converter smelting stage, a vacuum processing stage and a continuous casting stage, and then entering the step B.
B, determining whether the pouring furnace is a casting furnace or not according to the timestamp of the production furnace and the recorded count value of the pouring record based on the production stages corresponding to the sub-period of the production obtained in the step A, wherein the production furnace comprises the casting furnace, the submerged nozzle replacement furnace and the normal casting furnace;
judging whether the pouring heat is a submerged nozzle replacing furnace or not according to the blank pulling speed and the pouring duration time;
judging whether the casting heat is a casting furnace or not according to the recorded data value of the casting record under the same casting heat, and when the counted value of the casting record is zero, and the time stamp is the earliest under the same heat number, namely the casting furnace is started;
judging whether the pouring heat is a submerged nozzle replacement furnace or not, and determining that the pouring heat is the submerged nozzle replacement furnace when the blank pulling speed is reduced to a preset threshold value and the casting duration time is within a preset time range;
extracting each preset characteristic value of the corresponding historical process data set to form a characteristic vector value corresponding to each preset characteristic value in the historical process data set, combining each characteristic vector value corresponding to the historical process data set corresponding to the production stage to obtain a production heat set for generating a skin-lifting defect, and further obtaining each skin-lifting defect type generated in the production stage, wherein the skin-lifting defect type comprises a liquid level fluctuation defect and a process parameter quantity defect, the process parameter quantity comprises an oxygen blowing quantity, the lowest molten steel temperature of a tundish and the smallest molten steel weight of the tundish, and then entering the step C.
Step C, calculating and obtaining the skin-lifting defect rate corresponding to the skin-lifting defect type corresponding to the production stage based on a production heat collection of the skin-lifting defect generated by the skin-lifting defect type, namely obtaining the skin-lifting defect rate corresponding to the skin-lifting defect type corresponding to the production stage;
aiming at different skin-lifting defect types, determining the defect as a liquid level fluctuation defect when the liquid level fluctuation of molten steel in the casting process is larger than a preset fluctuation threshold value, and considering that the liquid level fluctuation of molten steel in a crystallizer is overlarge when the liquid level fluctuation between two adjacent time points is larger than 3 mm, as a representation of the liquid level fluctuation level of the crystallizer in the casting process of a whole ladle of molten steel, and considering that the liquid level fluctuation of the crystallizer in the casting process of the whole ladle of molten steel is overlarge when the value of the liquid level fluctuation is higher than a threshold value 2;
and D, calculating an average defect value of the process parameter based on each preset characteristic value of the historical process data set according to the skin warping defect corresponding to each process parameter, determining the average defect value as the process parameter defect when the average defect value is larger than a preset threshold value, and then entering the step D.
Step D, respectively aiming at different types of skin-lifting defects generated in the production stage, determining pouring heat when the skin-lifting defects are generated according to the skin-lifting defect rates respectively corresponding to the skin-lifting defect types in the production stage, combining characteristic vector values in historical process data sets corresponding to the skin-lifting defects under different pouring heat to obtain influencing factors for generating the skin-lifting defects, and combining the pouring heat to determine the generation positions of the skin-lifting defects.
Examples
According to the embodiment of the invention, through automatic judgment of a continuous casting pouring heat of molten steel, automatic judgment of a continuous casting water gap replacement heat of molten steel, characterization and calculation of a fluctuation level of a liquid level of a crystallizer, determination and calculation of pouring temperature of a tundish, calculation of the weight of the molten steel of the minimum tundish, calculation of heat of three pouring modes and calculation of a tilting defect contribution rate, calculation of influence of a single technological parameter, output and acquisition of comprehensive average tilting defect rate in each production subperiod, tilting defect rates of different pouring modes, tilting defect rate contribution values and a furnace number list caused by water changing openings, tilting defect rate contribution values and a furnace number list caused by overlarge fluctuation of the liquid level of the crystallizer, tilting defect rate contribution values and a furnace number list caused by overlarge oxygen blowing amount of molten steel vacuum treatment, tilting defect rate contribution values and furnace number lists caused by overlarge pouring temperature and tilting defect furnace number lists caused by overlarge liquid level of the molten steel of the tundish.
In a specific application of the invention, according to the tracing method, the following factors causing the skin warping defect are determined based on data of a specific production workshop: the tapping temperature of the converter is lower, the oxygen blowing amount in the vacuum treatment process is overlarge, the weight of the continuous casting tundish molten steel is lower, and the temperature of the tundish molten steel is lower. The corresponding improvement method is given as follows: the tapping temperature of the converter is properly raised (+8℃), the oxygen blowing amount of the vacuum treatment process is properly lowered (-15%), the minimum value limit of the molten steel weight of the continuous casting tundish is properly raised (+5 tons), and the minimum value limit of the molten steel temperature of the continuous casting tundish is properly raised (+6 ℃).
According to the improvement measures of the production process, the rate of the defects of the skin-lifting in the product is reduced month by month from the initial average of 2.20 percent to the subsequent average of 0.95 percent, and the output results show the magnitude and quantitative values of the influences of different process units, different process parameters, different pouring modes and the like on the defects of the skin-lifting from different dimensions, thereby providing clear reference and optimizing improvement direction for the specific improvement of the process operation in the production process. The relevant data are shown in table 1 below:
TABLE 1 skin lifting defect Rate
| Month number | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 |
| Rate of skin lifting defect | 2.20％ | 1.60％ | 1.50％ | 1.20％ | 0.90％ | 1.17％ | 0.82％ | 1.06％ | 0.95％ |
While the invention has been described with reference to preferred embodiments, it is not intended to be limiting. Those skilled in the art will appreciate that various modifications and adaptations can be made without departing from the spirit and scope of the present invention. Accordingly, the scope of the invention is defined by the appended claims.
Claims (8)
1. The hot rolled coil plate skin-lifting defect tracing method based on data analysis is used for obtaining defect types corresponding to different skin-lifting defects according to production data information of the skin-lifting defects in the process of producing the hot rolled coil plate, and further obtaining influence factors of the skin-lifting defects and occurrence positions of the skin-lifting defects, and is characterized by collecting and obtaining historical production data information of the hot rolled coil plate produced in a specified historical period, dividing the historical production data information into production subperiods according to a preset specified historical period, and executing the following steps according to the production subperiods respectively:
step A, extracting each preset appointed type of historical process data set contained in a production subperiod based on historical production data information, preprocessing the extracted historical process data set, determining a production stage corresponding to the production subperiod based on the preprocessed historical process data set by combining a preset corresponding relation between the production stage and a production heat, and then entering step B;
b, respectively aiming at each production stage, extracting each preset characteristic value of the corresponding historical process data set based on the production stage corresponding to the production sub-period obtained in the step A to form a characteristic vector value corresponding to each preset characteristic value in the historical process data set, combining each characteristic vector value corresponding to the historical process data set corresponding to the production stage to obtain a production heat set for generating the skin-lifting defect, further obtaining each skin-lifting defect type generated in the production stage, and then entering the step C;
step C, calculating and obtaining the skin-lifting defect rate corresponding to the skin-lifting defect type corresponding to the production stage based on a production heat collection of the skin-lifting defect generated by the skin-lifting defect type, namely obtaining the skin-lifting defect rate corresponding to the skin-lifting defect type corresponding to the production stage, and then entering the step D;
step D, respectively aiming at different types of skin-lifting defects generated in the production stage, determining pouring heat when the skin-lifting defects are generated according to the skin-lifting defect rates respectively corresponding to the skin-lifting defect types in the production stage, combining characteristic vector values in historical process data sets corresponding to the skin-lifting defects under different pouring heat to obtain influencing factors for generating the skin-lifting defects, and combining the pouring heat to determine the generation positions of the skin-lifting defects.
2. The hot rolled plate bending defect tracing method based on data analysis according to claim 1, wherein in the step a, preprocessing is performed on each preset specified type of historical process data set, the complete value in the process data is extracted, the abnormal value is removed, and the preset specified type of historical process data set comprises furnace time data, quality detection data, parameter data, steel grade data and interface data corresponding to the production subperiod;
the production stage comprises a converter smelting stage, a vacuum treatment stage and a continuous casting stage.
3. The method for tracing the warping defect of the hot rolled coil based on data analysis according to claim 2, wherein in the step B, based on a production stage and a preset corresponding relation between the production stage and a production heat, the production heat comprises a casting start furnace, a submerged nozzle replacement furnace and a normal casting furnace, and whether the casting heat is the casting start furnace is determined according to a timestamp of the production heat and a record count value of a casting record;
judging whether the pouring heat is a submerged nozzle replacing furnace according to the blank pulling speed and the pouring duration time.
4. The method for tracing the warping defect of the hot rolled coil based on data analysis according to claim 3, wherein under the same casting heat, judging whether the casting heat is a casting start according to the recorded data value of casting records, and when the counted value of the casting records is zero and the timestamp is earliest under the same heat, the casting start is the casting start;
judging whether the pouring heat is a submerged nozzle replacing furnace or not, and determining that the pouring heat is the submerged nozzle replacing furnace when the blank pulling speed is reduced to a preset threshold value and the casting duration time is within a preset time range.
5. The method for tracing the skin-lifting defect of the hot rolled coil based on the data analysis according to claim 1, wherein in the step B, the skin-lifting defect type comprises a liquid level fluctuation defect and a process parameter quantity defect, and the process parameter quantity comprises oxygen blowing quantity, minimum molten steel temperature of a tundish and minimum molten steel weight of the tundish.
6. The method for tracing the hot rolled coil tilting defects based on data analysis according to claim 5, wherein the method is characterized in that the method is determined to be a liquid level fluctuation defect when the liquid level fluctuation of molten steel in the casting process is greater than a preset fluctuation threshold value for different tilting defect types;
and calculating an average defect value of the process parameter based on each preset characteristic value of the historical process data set according to the skin warping defect corresponding to each process parameter, and determining the average defect value as the process parameter defect when the average defect value is larger than a preset threshold value.
7. A hot rolled coil warping defect tracing system based on data analysis is characterized by comprising:
the module is used for extracting each historical process data set of preset designated types contained in the production subperiod, preprocessing the extracted historical process data sets and determining the production stage corresponding to the production subperiod by combining the preset corresponding relation between the production stage and the production heat;
the module is used for respectively extracting each preset characteristic value of the corresponding historical process data set aiming at each production stage to form a characteristic vector value corresponding to each preset characteristic value in the historical process data set, and combining each characteristic vector value corresponding to the historical process data set corresponding to the production stage to obtain a production heat set for generating the skin warping defect;
the module is used for obtaining the corresponding skin-lifting defect rate of each skin-lifting defect type in the production stage;
and the module is used for respectively aiming at different types of skin-lifting defects generated in the production stage, determining pouring heat when the skin-lifting defects are generated according to the skin-lifting defect rates respectively corresponding to the skin-lifting defect types in the production stage, combining all characteristic vector values in historical process data sets corresponding to the skin-lifting defects under different pouring heat to obtain influencing factors for generating the skin-lifting defects, and combining the pouring heat to determine the generation positions of the skin-lifting defects.
8. A computer readable medium storing software, wherein the software comprises instructions executable by one or more computers, which when executed by the one or more computers perform the hot rolled sheet skin-lifting defect tracing method based on data analysis of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210178234.XA CN114781110B (en) | 2022-02-25 | 2022-02-25 | Hot rolled coil plate warping defect tracing method and system based on data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210178234.XA CN114781110B (en) | 2022-02-25 | 2022-02-25 | Hot rolled coil plate warping defect tracing method and system based on data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114781110A CN114781110A (en) | 2022-07-22 |
| CN114781110B true CN114781110B (en) | 2024-04-02 |
Family
ID=82424066
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210178234.XA Active CN114781110B (en) | 2022-02-25 | 2022-02-25 | Hot rolled coil plate warping defect tracing method and system based on data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114781110B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118691165A (en) * | 2024-08-26 | 2024-09-24 | 南京先维信息技术有限公司 | Aluminum smelting product quality monitoring and tracing method and system based on big data modeling |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130046711A (en) * | 2011-10-28 | 2013-05-08 | 현대제철 주식회사 | Device for predicting edge defect of hot-rolled steel sheet coil and method therefor |
| CN110000221A (en) * | 2019-04-09 | 2019-07-12 | 鞍钢股份有限公司 | Method for improving linear warping defect of non-oriented silicon steel hot-rolled edge |
| CN113578976A (en) * | 2021-07-28 | 2021-11-02 | 北京首钢股份有限公司 | Production method and production system of hot-rolled electrical steel capable of controlling edge warping |
-
2022
- 2022-02-25 CN CN202210178234.XA patent/CN114781110B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130046711A (en) * | 2011-10-28 | 2013-05-08 | 현대제철 주식회사 | Device for predicting edge defect of hot-rolled steel sheet coil and method therefor |
| CN110000221A (en) * | 2019-04-09 | 2019-07-12 | 鞍钢股份有限公司 | Method for improving linear warping defect of non-oriented silicon steel hot-rolled edge |
| CN113578976A (en) * | 2021-07-28 | 2021-11-02 | 北京首钢股份有限公司 | Production method and production system of hot-rolled electrical steel capable of controlling edge warping |
Non-Patent Citations (1)
| Title |
|---|
| 付小龙 ; .热轧翘皮缺陷连铸工序影响因素及控制措施.技术与市场.2017,(第10期),第138页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114781110A (en) | 2022-07-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114781110B (en) | Hot rolled coil plate warping defect tracing method and system based on data analysis | |
| CN115106499B (en) | Method and system for judging abnormal fluctuation of liquid level of crystallizer | |
| CN110929355B (en) | Method for predicting crack risk of continuous casting billet and application thereof | |
| CN110930065A (en) | Casting blank quality determination method and system | |
| CN114985697B (en) | Crystallizer liquid level fluctuation monitoring method and system | |
| CN110989510A (en) | Hot galvanizing product full-process quality control and grade automatic judgment system | |
| CN110628981A (en) | Solidification experience method for defining splashing in converter blowing period | |
| CN108941496B (en) | Real-time tracking and controlling system and method for quality of steelmaking continuous casting process | |
| CN113092712B (en) | Method for evaluating quality of casting blank of outer plate exposed part for high-end automobile | |
| CN106844831B (en) | Method for optimizing IF steel smelting parameters and reducing cold rolling inclusion defects | |
| CN111421119A (en) | Online prediction method for longitudinal cracks on surface of continuous casting slab | |
| CN115094193A (en) | Intelligent molten iron pretreatment desulfurization system based on data mining | |
| CN112149966B (en) | Method for quality judgment based on steelmaking multi-data-source aggregation guidance process | |
| CN113578976B (en) | Production method and production system for hot-rolled electrical steel with edge skin tilting control function | |
| CN114398785A (en) | Method and device for processing key smelting data of inclusions in steel and storage medium | |
| CN117171936A (en) | Slab quality prediction method for extracting real-time characteristic value of crystallizer based on defect mechanism | |
| CN112222201A (en) | Method and device for prejudging abnormal operation of rolling line equipment and storage medium | |
| CN110586891A (en) | Method for evaluating liquid level control precision of continuous casting crystallizer | |
| Prakash¹ et al. | Detection and Analysis of Clogging in a Submerged Entry Nozzle Using Deep Learning | |
| CN115239155A (en) | Prediction method and device for stamping cracking of sheet strip steel | |
| WO2024084824A1 (en) | Defect occurrence factor estimation device, defect occurrence factor estimation method, learning method for defect occurrence factor estimation model, operation condition determination method, and steel product production method | |
| CN118013426B (en) | Steel product inclusion causal effect optimization method, system, electronic equipment and medium | |
| CN116911167A (en) | Slab flaw detection qualification rate prediction method based on industrial big data | |
| CN113112120B (en) | Online precision evaluation method for hot-rolled strip steel side press | |
| CN117196355A (en) | System and method for tracing quality defect factors of continuous casting slab |
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 |