CN113828641A - Method for processing deviation curve between frames of finish rolling strip steel based on machine vision - Google Patents

Method for processing deviation curve between frames of finish rolling strip steel based on machine vision Download PDF

Info

Publication number
CN113828641A
CN113828641A CN202111382991.0A CN202111382991A CN113828641A CN 113828641 A CN113828641 A CN 113828641A CN 202111382991 A CN202111382991 A CN 202111382991A CN 113828641 A CN113828641 A CN 113828641A
Authority
CN
China
Prior art keywords
width
strip steel
deviation
difference
value
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.)
Granted
Application number
CN202111382991.0A
Other languages
Chinese (zh)
Other versions
CN113828641B (en
Inventor
何海楠
丁吉杰
徐冬
彭功状
杨荃
王晓晨
闫书宗
周杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
University of Science and Technology Beijing USTB
Original Assignee
University of Science and Technology Beijing USTB
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by University of Science and Technology Beijing USTB filed Critical University of Science and Technology Beijing USTB
Priority to CN202111382991.0A priority Critical patent/CN113828641B/en
Publication of CN113828641A publication Critical patent/CN113828641A/en
Application granted granted Critical
Publication of CN113828641B publication Critical patent/CN113828641B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
    • B21B—ROLLING OF METAL
    • B21B37/00—Control devices or methods specially adapted for metal-rolling mills or the work produced thereby
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
    • B21B—ROLLING OF METAL
    • B21B38/00—Methods or devices for measuring, detecting or monitoring specially adapted for metal-rolling mills, e.g. position detection, inspection of the product

Landscapes

  • Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Control Of Metal Rolling (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

The invention provides a machine vision-based method for processing a deviation curve between finish rolling strip steel racks, and belongs to the technical field of steel rolling automation. The method comprises the steps of detecting strip steel by using a binocular linear array camera arranged at the top end of a rack, extracting strip steel edges from collected strip steel images, and obtaining edge coordinates of the left side and the right side of the strip steel images; and then calculating the width and the deviation of the strip steel, calculating the difference value between the actual strip steel width measured by the outlet width gauge and the strip steel width obtained by detection, forming a judgment model through data fitting, filtering deviation data corresponding to the width difference exceeding a threshold value, and taking the previous deviation value as the deviation numerical value of the point. The method comprises the steps of calculating the difference value between the measured strip steel width and the actual width at the detection moment, and filtering deviation data corresponding to the width difference data with the difference value exceeding the threshold value, so that the purpose of removing noise points by the deviation curve is achieved.

Description

Method for processing deviation curve between frames of finish rolling strip steel based on machine vision
Technical Field
The invention relates to the technical field of steel rolling automation, in particular to a method for processing a deviation curve between frames of finish rolling strip steel based on machine vision.
Background
The hot-rolled strip steel is an important steel product and is widely applied to various departments of national economy such as buildings, bridges, ships, vehicles and the like. Under the background of product structure adjustment, cost reduction and efficiency improvement in domestic steel industry at present, the product capacity with surplus capacity, low technical content and additional value is gradually compressed or quits from various large steel manufacturers, the hot rolled strip steel continuously develops a new application field in continuous product structure adjustment and quality optimization, the steel market gradually develops from cold rolling to hot rolling, and the demand of the hot rolled strip steel is determined to continuously climb.
In the prior finish rolling process, the deviation detection of the strip steel mainly depends on the manual judgment and correction of workers, thereby greatly increasing the uncertainty of the deviation control of the strip steel, leading to poor control effect and stability and being difficult to accurately obtain a deviation numerical value.
At present, in a certain domestic steel mill, the construction of a finish rolling strip steel deviation detection system is completed, a non-contact strip steel deviation online measurement scheme which is based on a machine vision technology and takes image detection as a means is adopted, the characteristics of high precision and strong robustness can meet the aim of accurately measuring strip steel deviation data, the strip steel deviation data in the finish rolling process can be accurately and effectively acquired in real time, and the subjective assumption of workers is eliminated.
Through the system, the width data and the deviation data of the strip steel can be obtained, the deviation of the strip steel is displayed in real time, but the problems of water vapor, equipment shaking and the like exist due to poor field working environment, and the displayed deviation curve of the strip steel has a plurality of noise points, so that the judgment and adjustment of operators are influenced, and the subsequent plate shape control is influenced to a certain degree.
In the prior art, a curve fitting method is mostly adopted for a curve filtering method, the method can fit observation data through a proper curve type, but only can reflect the general trend of the data, the curve has no local fluctuation as much as possible, and an accurate deviation value needs to be obtained in the process of rolling the strip steel for subsequent adjustment, so the method is not suitable for the deviation curve processing between the racks of the finish rolling strip steel.
Disclosure of Invention
The invention aims to provide a method for processing a deviation curve between frames of finish rolling strip steel based on machine vision.
The method includes the steps that a binocular linear array camera is used for collecting strip steel images in real time, the width and deviation of the images are calculated through an edge detection means, and noise points are filtered through the difference between the calculated width and the actual strip steel width.
The method comprises the following steps:
s1: acquiring edge coordinates of a strip steel image:
the method comprises the steps that two cameras are used for simultaneously collecting strip steel images at the same position, a sub-pixel edge detection algorithm is adopted for detecting the edges of the images, and the left and right edge coordinates of the strip steel images at the collecting moment are obtained;
s2: calculating the width of the strip steel at the collection time and the deviation amount relative to the rolling center line in the S1;
s3: acquiring the set width data of the strip steel of the outlet width gauge, determining the width difference threshold value of the strip steel with the corresponding width, and making the difference between the set width and the calculated value of the strip steel width in S2;
s4: and filtering the deviation value of the deviation moment corresponding to the width difference exceeding the width difference threshold value obtained by difference calculation in the step S3, and taking the previous point as the deviation value of the current point.
Two cameras in the S1 are binocular linear array cameras, and are respectively mounted above the racks in parallel, and can acquire strip steel images between adjacent racks, and the mounting schematic diagram is shown in fig. 2;
the calculation process of the width of the strip steel and the deviation amount relative to the rolling center line in the S2 is as follows:
the width of the detected strip steel is measured by the imaging principle of a binocular camera
Figure 6769DEST_PATH_IMAGE001
Comprises the following steps:
Figure 10497DEST_PATH_IMAGE002
wherein the content of the first and second substances,
Figure 858367DEST_PATH_IMAGE003
the length of the camera optical center distance calibration plane is in mm;
Figure 455702DEST_PATH_IMAGE004
the distance from the intersection point of the optical axis of the left camera and the calibration plane to the left edge of the projection of the strip steel on the calibration plane is in mm;
Figure 414431DEST_PATH_IMAGE005
the distance from the intersection point of the optical axis of the right camera and the calibration plane to the right edge of the projection of the strip steel on the calibration plane is in mm;
Figure 272665DEST_PATH_IMAGE006
the camera external parameters represent the inclination angles of the optical axes of the two cameras relative to a vertical plane, and the unit is DEG, and the camera external parameters are obtained through calibration;
Figure 291437DEST_PATH_IMAGE007
the focal length of the camera is obtained by calibration and the unit is mm;
Figure 625335DEST_PATH_IMAGE008
the horizontal distance between the two cameras is obtained by calibration and the unit is mm;
the deviation of the strip steel relative to the rolling center line is half of the distance difference between the strip steel edge corresponding to the two cameras and the rolling center line, and the deviation
Figure 387755DEST_PATH_IMAGE009
Comprises the following steps:
Figure 366075DEST_PATH_IMAGE010
Figure 290169DEST_PATH_IMAGE011
in a calibration plane, the difference value of the distances between the optical axes of the two cameras and the rolling center line is obtained through calibration and has the unit of mm.
S3 specifically includes:
s31: the method comprises the following steps of sampling strip steel with different widths for multiple times, wherein the sampling frequency of the strip steel with the same width is not less than 1000 coils, establishing a functional relation between a width deviation standard and the width of the strip steel, and having a linear functional relation:
Figure 862095DEST_PATH_IMAGE012
wherein the content of the first and second substances,
Figure 162627DEST_PATH_IMAGE013
is the width of the strip steel, and the unit is mm;
Figure 261033DEST_PATH_IMAGE014
the width deviation is taken as a width deviation standard and is the corresponding theoretical width deviation under the actual width of the strip steel, the width deviation outside the standard range is taken as noise point, and the unit is mm; the strip steel deviation standard is obtained by averaging the width deviations of a plurality of rolls of strip steel with the same width so as to determine the actual width deviation under the corresponding strip steel width, establish a relation between the width deviation standard and the strip steel width, and after substituting the relation into the detected strip steel width,the deviation benchmark of the strip steel can be obtained, and the threshold range is locked;
Figure 356028DEST_PATH_IMAGE015
for the first-order fit coefficient,
Figure 664518DEST_PATH_IMAGE016
fitting coefficients of constant terms are all dimensionless;
s32: communicating the strip steel width data measured by the detected steel coil F7 outlet width gauge, and determining the width difference threshold value under the strip steel width:
the set width of the communication strip steel is substituted into an S31 formula, and the corresponding width difference reference can be determinedy；
Further setting the width difference threshold value of the strip steel with the corresponding width
Figure 565478DEST_PATH_IMAGE017
；
The threshold range is determined by modifying the threshold range to obtain a filtered curve, and under the range, the curve is smooth, the noise points are few, and the normal running deviation value cannot be filtered;
s33: communicating the calculated width and the corresponding deviation value of the strip steel at all detection moments, and calculating the width deviation between the calculated width and the set width of the strip steel:
Figure 190494DEST_PATH_IMAGE018
wherein the content of the first and second substances,
Figure 394074DEST_PATH_IMAGE019
width deviation in mm;
Figure 799647DEST_PATH_IMAGE020
calculating the width, which is calculated by S2 and has the unit of mm;
Figure 707561DEST_PATH_IMAGE021
setting the width as the width of the strip steel obtained by an F7 outlet width gauge, wherein the unit is mm;
the S4 specifically comprises the following steps:
if it is
Figure 639613DEST_PATH_IMAGE022
Figure 341990DEST_PATH_IMAGE023
Or
Figure 234860DEST_PATH_IMAGE022
Figure 680885DEST_PATH_IMAGE024
Then, the point is filtered, and the previous point offset value is taken as the current point offset value.
Wherein the content of the first and second substances,
Figure 218176DEST_PATH_IMAGE022
is the width deviation in mm.
The method adopts the width difference data obtained by the difference between the detected width and the set width as the filtering reference, because the influence of water vapor and equipment shake exists in the process of rolling the strip steel, meanwhile, during calibration, the detection deviation can be caused due to installation problems, the width data measured by a detection instrument is influenced, a certain error is generated between the width data and the actual width of the strip steel, the influence of the error can be reduced by adopting the width difference data, and the filtering accuracy is improved.
The technical scheme of the invention has the following beneficial effects:
in the scheme, the binocular matrix camera is adopted for detection, so that the influence of the loop angle and the like on the detection precision in the rolling process is effectively eliminated; the width difference data obtained by the difference between the detected width and the set width is used as a filtering reference, so that the installation error of the camera and the influence on the detection result caused by the field working environment are effectively reduced, and the filtering accuracy is improved; corresponding width difference threshold values are determined for steel coils with different widths, and after noise points are filtered out, the previous point is used as a deviation value of the point, so that the purpose of processing a deviation curve is achieved.
Drawings
FIG. 1 is a flow chart of a method for processing a deviation curve between frames of finish rolling strip steel based on machine vision;
FIG. 2 is a schematic view of a binocular linear array camera installation;
FIG. 3 is a strip edge image extracted by a camera;
FIG. 4 is a fitting curve of the set width and the width difference of the strip steel obtained according to the data of an F7 outlet width gauge;
FIG. 5 is a deviation curve between strip steel frames without width filtering;
FIG. 6 is a deviation curve between the strip steel frames after width filtering.
Detailed Description
In order to make the technical problems, technical solutions and advantages of the present invention more apparent, the following detailed description is given with reference to the accompanying drawings and specific embodiments.
The invention provides a method for processing a deviation curve between frames of finish rolling strip steel based on machine vision.
As shown in fig. 1, the method comprises the steps of:
s1: acquiring edge coordinates of a strip steel image:
the method comprises the steps that two cameras are used for simultaneously collecting strip steel images at the same position, a sub-pixel edge detection algorithm is adopted for detecting the edges of the images, and the left and right edge coordinates of the strip steel images at the collecting moment are obtained;
s2: calculating the width of the strip steel at the collection time and the deviation amount relative to the rolling center line in the S1;
s3: acquiring the set width data of the strip steel of the outlet width gauge, determining the width difference threshold value of the strip steel with the corresponding width, and making the difference between the set width and the calculated value of the strip steel width in S2;
s4: and filtering the deviation value of the deviation moment corresponding to the width difference exceeding the width difference threshold value obtained by difference calculation in the step S3, and taking the previous point as the deviation value of the current point.
The following description is given with reference to specific examples.
In the specific treatment process, the following steps are carried out.
S1: acquiring edge coordinates of a strip steel image:
the method comprises the following steps of (1) simultaneously acquiring strip steel images at the same position by using two cameras (the installation positions of the cameras are shown in figure 2, and extracted strip steel edge images are shown in figure 3), and detecting the edges of the images by adopting a sub-pixel edge detection algorithm to obtain the left and right edge coordinates of the strip steel images at the acquisition moment;
the external parameter and internal parameter values detected by the binocular linear array camera are shown in the following table:
TABLE 1 Camera parameter values
Figure 91454DEST_PATH_IMAGE025
S2: calculating the width of the strip steel and the deviation amount relative to the rolling center line at the moment;
obtained by the imaging principle of a binocular camera and the width of the detected strip steel
Figure 471620DEST_PATH_IMAGE001
Comprises the following steps:
Figure 455757DEST_PATH_IMAGE026
wherein the content of the first and second substances,
Figure 362402DEST_PATH_IMAGE003
the length of the camera optical center distance calibration plane is measured by field calibration and the unit is mm;
Figure 406581DEST_PATH_IMAGE004
the distance from the intersection point of the optical axis of the left camera and the calibration plane to the left edge of the projection of the strip steel on the calibration plane is acquired by communication left camera equipment and the unit is mm;
Figure 274043DEST_PATH_IMAGE005
from the intersection point of the right camera optical axis and the calibration plane to the right edge of the strip steel projected on the calibration planeDistance, which is acquired by the camera equipment on the right side of the communication and is in mm;
Figure 61870DEST_PATH_IMAGE006
the external parameters of the cameras are obtained through calibration, and represent the inclination angles of the optical axes of the two cameras relative to a vertical plane, and the unit is DEG;
Figure 573754DEST_PATH_IMAGE007
calibrating the obtained internal parameters, representing the focal length of the camera, and the unit is mm;
Figure 788835DEST_PATH_IMAGE008
calibrating the obtained external parameters of the cameras, and representing the horizontal distance between the two cameras, wherein the unit is mm;
the distances from the intersection point of the camera optical axis and the calibration plane obtained by the communication of the cameras at the left side and the right side to the projection edge of the strip steel on the calibration plane are respectively as follows:
Figure 878014DEST_PATH_IMAGE027
so that the strip width of the strip to be detected is at the moment of detection
Figure 390903DEST_PATH_IMAGE028
The deviation of the strip steel relative to the rolling center line is half of the distance difference between the strip steel edge corresponding to the two cameras and the rolling center line, and the deviation
Figure 819611DEST_PATH_IMAGE029
Comprises the following steps:
Figure 267910DEST_PATH_IMAGE030
Figure 47647DEST_PATH_IMAGE011
calibrating the obtained external parameters of the cameras, and representing the difference between the distances between the optical axes of the two cameras and the rolling center line in a calibration plane, wherein the unit is mm;
the deviation of the detected strip steel at the detection time is calculated as
Figure 442856DEST_PATH_IMAGE031
In the formula, a negative sign indicates deviation towards the transmission side direction;
s3: acquiring the set width data of the strip steel of the outlet width gauge, determining the width difference threshold value of the strip steel with the corresponding width, and making the difference between the set width and the calculated value of the strip steel width in S2;
s31: sampling the band steel with different widths for many times, wherein the sampling frequency of the band steel with the same width is not less than 1000 coils, establishing a functional relation, and obtaining a linear functional relation with the width deviation standard being the band steel width:
Figure 663753DEST_PATH_IMAGE012
wherein the content of the first and second substances,
Figure 282953DEST_PATH_IMAGE013
is the width of the strip steel, and the unit is mm;
Figure 549986DEST_PATH_IMAGE032
is the width deviation standard and has the unit of mm.
Taking the F2 stand as an example, the results obtained by sampling the strips of different widths for multiple times are shown in the following table:
TABLE 2
Figure 483307DEST_PATH_IMAGE033
The fitted curve is as in fig. 4;
the corresponding functional relation is obtained as follows:
Figure 807978DEST_PATH_IMAGE034
s32: the communication is set for the width data of the strip steel measured by the width meter at the outlet of the detected steel coil F7:
the set width of the detected strip steel is obtained from an F7 outlet width gauge
Figure 801342DEST_PATH_IMAGE035
And substituting the relational expression to obtain the strip steel width difference with the corresponding width as follows:
Figure 352409DEST_PATH_IMAGE036
thus, the threshold range was determined to be [36.26,56.26]
S33: the communication L2 server obtains the calculated width of the strip steel at all the detection moments and the corresponding deviation value, and calculates the width deviation between the calculated width of the strip steel and the set width;
Figure 823842DEST_PATH_IMAGE037
wherein the content of the first and second substances,
Figure 19331DEST_PATH_IMAGE019
width deviation in mm;
Figure 183596DEST_PATH_IMAGE020
the detection width is calculated by S2 and the unit is mm;
Figure 956380DEST_PATH_IMAGE021
the set width is the strip width data obtained by an outlet width gauge of F7 and is obtained by server communication and the unit is mm.
S4: filtering the deviation value of the deviation moment corresponding to the width exceeding the threshold value, and taking the previous point as the deviation value of the point:
detection width calculated by S2
Figure 231503DEST_PATH_IMAGE038
;
Figure 796346DEST_PATH_IMAGE039
And if the current point is not within the threshold range, filtering the point, and taking the previous point offset value as the current point offset value.
And similarly, width difference data of the whole roll of strip steel at different detection moments are obtained, deviation values corresponding to the width difference data which are not in the threshold value range are filtered, and the deviation value of the previous point is used as the deviation value of the current point.
The off-tracking image before filtering is as shown in FIG. 5;
noise is filtered according to the width difference, and the obtained filtered image is as shown in fig. 6.
The method for processing the deviation curve between the frames of the finish rolling strip steel is applied to a finish rolling measurement and control automatic deviation rectifying system of a 2250mm hot continuous rolling unit for large-scale industrial application, and then a very remarkable curve filtering effect is obtained. According to the display of the deviation image on the display screen of the deviation detection and control system between the finishing mill frames, the method can find that after filtering, the curve noise point is obviously less, the curve is more approximate to smooth, and the curve jitter phenomenon caused by field equipment and working environment is well reduced after the method is applied.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention as defined in the appended claims.

Claims (5)

1. A method for processing a deviation curve between frames of finish rolling strip steel based on machine vision is characterized by comprising the following steps:
s1: acquiring edge coordinates of a strip steel image:
the method comprises the steps that two cameras are used for simultaneously collecting strip steel images at the same position, a sub-pixel edge detection algorithm is adopted for detecting the edges of the images, and the left and right edge coordinates of the strip steel images at the collecting moment are obtained;
s2: calculating the width of the strip steel at the collection time and the deviation amount relative to the rolling center line in the S1;
s3: acquiring the set width data of the strip steel of the outlet width gauge, determining the width difference threshold value of the strip steel with the corresponding width, and making the difference between the set width and the calculated value of the strip steel width in S2;
s4: and filtering the deviation value of the deviation moment corresponding to the width difference exceeding the width difference threshold value obtained by difference calculation in the step S3, and taking the previous point as the deviation value of the current point.
2. The machine vision-based off-tracking curve processing method between stands of finish rolling strip steel according to claim 1, wherein the two cameras in the step S1 are binocular linear cameras which are respectively installed above the stands in parallel and can acquire strip steel images between adjacent stands.
3. The method of claim 1, wherein the calculation of the deviation between the strip steel strip rolling stands with respect to the width of the strip steel and the rolling center line in S2 is as follows:
the width of the detected strip steel is measured by the imaging principle of a binocular camera
Figure 571346DEST_PATH_IMAGE001
Comprises the following steps:
Figure 222908DEST_PATH_IMAGE002
wherein the content of the first and second substances,
Figure 799383DEST_PATH_IMAGE003
the length of the camera optical center distance calibration plane is in mm;
Figure 929013DEST_PATH_IMAGE004
the distance from the intersection point of the optical axis of the left camera and the calibration plane to the left edge of the projection of the strip steel on the calibration plane is in mm;
Figure 664756DEST_PATH_IMAGE005
the distance from the intersection point of the optical axis of the right camera and the calibration plane to the right edge of the projection of the strip steel on the calibration plane is in mm;
Figure 221640DEST_PATH_IMAGE006
the camera external parameters represent the inclination angles of the optical axes of the two cameras relative to a vertical plane, and the unit is DEG, and the camera external parameters are obtained through calibration;
Figure 285410DEST_PATH_IMAGE007
the focal length of the camera is obtained by calibration and the unit is mm;
Figure 218731DEST_PATH_IMAGE008
the horizontal distance between the two cameras is obtained by calibration and the unit is mm;
the deviation of the strip steel relative to the rolling center line is half of the distance difference between the strip steel edge corresponding to the two cameras and the rolling center line, and the deviation
Figure 559714DEST_PATH_IMAGE009
Comprises the following steps:
Figure 287499DEST_PATH_IMAGE010
Figure 838566DEST_PATH_IMAGE011
in the plane of the calibrationAnd the difference between the distances between the optical axes of the two cameras and the rolling center line is obtained by calibration and has the unit of mm.
4. The machine vision-based off-tracking curve processing method between finish rolling strip steel frames as claimed in claim 1, wherein the step S3 is specifically as follows:
s31: the method comprises the following steps of sampling strip steel with different widths for multiple times, wherein the sampling frequency of the strip steel with the same width is not less than 1000 coils, establishing a functional relation between a width deviation standard and the width of the strip steel, and having a linear functional relation:
Figure 309998DEST_PATH_IMAGE012
wherein the content of the first and second substances,
Figure 754755DEST_PATH_IMAGE013
is the width of the strip steel, and the unit is mm;
Figure 919020DEST_PATH_IMAGE014
the width deviation is taken as a width deviation standard and is the corresponding theoretical width deviation under the actual width of the strip steel, the width deviation outside the standard range is taken as noise point, and the unit is mm;
Figure 160646DEST_PATH_IMAGE015
for the first-order fit coefficient,
Figure 232507DEST_PATH_IMAGE016
fitting coefficients of constant terms are all dimensionless;
s32: the communication is carried out on the preset width data of the strip steel measured by the outlet width gauge of the detected steel coil F7, and the width difference threshold value under the width of the strip steel is determined:
the set width of the communication strip steel is brought into an S31 formula, and the corresponding width difference reference is determined
Figure 610398DEST_PATH_IMAGE017
；
Setting the width difference threshold value of the strip steel with the corresponding width as
Figure 617669DEST_PATH_IMAGE018
；
S33: communicating the calculated width and the corresponding deviation value of the strip steel at all detection moments, and calculating the width deviation between the calculated width and the set width of the strip steel:
Figure 81011DEST_PATH_IMAGE019
wherein the content of the first and second substances,
Figure 956563DEST_PATH_IMAGE020
width deviation in mm;
Figure 188961DEST_PATH_IMAGE021
calculating the width, which is calculated by S2 and has the unit of mm;
Figure 881980DEST_PATH_IMAGE022
the set width is the width of the strip steel obtained by an F7 outlet width gauge, and the unit is mm.
5. The machine vision-based off-tracking curve processing method between finish rolling strip steel frames according to claim 1, wherein the step S4 specifically comprises the steps of:
if it is
Figure 567039DEST_PATH_IMAGE023
Figure 246282DEST_PATH_IMAGE024
Or
Figure 333187DEST_PATH_IMAGE023
Figure 947839DEST_PATH_IMAGE025
Filtering the point, and taking the previous point running deviation value as the current point running deviation value;
wherein the content of the first and second substances,
Figure 120194DEST_PATH_IMAGE023
is the width deviation in mm.
CN202111382991.0A 2021-11-22 2021-11-22 Method for processing deviation curve between frames of finish rolling strip steel based on machine vision Active CN113828641B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111382991.0A CN113828641B (en) 2021-11-22 2021-11-22 Method for processing deviation curve between frames of finish rolling strip steel based on machine vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111382991.0A CN113828641B (en) 2021-11-22 2021-11-22 Method for processing deviation curve between frames of finish rolling strip steel based on machine vision

Publications (2)

Publication Number Publication Date
CN113828641A true CN113828641A (en) 2021-12-24
CN113828641B CN113828641B (en) 2022-03-18

Family

ID=78971435

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111382991.0A Active CN113828641B (en) 2021-11-22 2021-11-22 Method for processing deviation curve between frames of finish rolling strip steel based on machine vision

Country Status (1)

Country Link
CN (1) CN113828641B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115090695A (en) * 2022-07-01 2022-09-23 北京科技大学 Continuous control method for tail deviation of strip steel between finishing mill frames based on machine vision

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS62235515A (en) * 1986-04-05 1987-10-15 Nippon Steel Corp Identification of changed position of strip steel thickness and width
CN107243511A (en) * 2017-06-15 2017-10-13 宁波宝新不锈钢有限公司 Cold-strip Steel Surface roughness online detection instrument and its recurrence smooth adaptive filtering method
CN110834033A (en) * 2018-08-17 2020-02-25 上海梅山钢铁股份有限公司 Automatic deviation rectifying control method for hot continuous rolling finishing mill group strip steel
CN112801966A (en) * 2021-01-21 2021-05-14 北京科技大学设计研究院有限公司 Online detection method for hot-rolled strip steel deviation
CN113042538A (en) * 2021-03-03 2021-06-29 首钢京唐钢铁联合有限责任公司 Control method and device for rolling deviation of hot rolled strip steel

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS62235515A (en) * 1986-04-05 1987-10-15 Nippon Steel Corp Identification of changed position of strip steel thickness and width
CN107243511A (en) * 2017-06-15 2017-10-13 宁波宝新不锈钢有限公司 Cold-strip Steel Surface roughness online detection instrument and its recurrence smooth adaptive filtering method
CN110834033A (en) * 2018-08-17 2020-02-25 上海梅山钢铁股份有限公司 Automatic deviation rectifying control method for hot continuous rolling finishing mill group strip steel
CN112801966A (en) * 2021-01-21 2021-05-14 北京科技大学设计研究院有限公司 Online detection method for hot-rolled strip steel deviation
CN113042538A (en) * 2021-03-03 2021-06-29 首钢京唐钢铁联合有限责任公司 Control method and device for rolling deviation of hot rolled strip steel

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
徐冬等: "基于机器视觉的热轧中间坯镰刀弯在线检测系统", 《中南大学学报(自然科学版)》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115090695A (en) * 2022-07-01 2022-09-23 北京科技大学 Continuous control method for tail deviation of strip steel between finishing mill frames based on machine vision
CN115090695B (en) * 2022-07-01 2023-08-08 北京科技大学 Continuous control method for strip steel tail deviation between finishing mill frames based on machine vision

Also Published As

Publication number Publication date
CN113828641B (en) 2022-03-18

Similar Documents

Publication Publication Date Title
CN109489566B (en) Lithium battery diaphragm material slitting width detection method, detection system and device
CN103471531B (en) The online non-contact measurement method of axial workpiece linearity
CN111421001B (en) Online accurate centering system of high-speed wire rod mill and centering method thereof
CN113828641B (en) Method for processing deviation curve between frames of finish rolling strip steel based on machine vision
CN110449471B (en) Method for detecting parallel relation of rollers
CN208505241U (en) A kind of measuring mechanism of steel rolling board width
CN108833912A (en) A kind of measurement method and system of video camera machine core optical axis center and field angle
CN112801966B (en) Online detection method for deviation of hot rolled strip steel
CN102944559A (en) Vision measurement method for anisotropic performance parameters in sheet forming
CN106984651B (en) Online control system for improving thickness control precision of rolled piece
CN106600592A (en) Track long chord measurement method based on the splicing of continuous frame images
CN114348735A (en) Weaving is with weaving cloth intelligence conveyer
CN114119483A (en) Image processing technology-based quality detection method and device for light wallboard for building
CN113607058B (en) Straight blade size detection method and system based on machine vision
CN117657859A (en) Battery cell winding deviation correction control device and control method
CN113649539B (en) Judging device for continuous casting secondary cooling water nozzle state
CN105203024A (en) Multiple sensor integrated icing photogrammetric method for power transmission line
CN112258466A (en) Cold-rolled strip vibration line online detection system and method based on gray level processing
KR100397630B1 (en) Roll eccentricity controll method of hot strip mill plant
CN111389909A (en) Method for on-line verification of measurement accuracy of thickness gauge
CN105290116A (en) Method for controlling transverse rolling width and longitudinal rolling width of moderately-thick plate
CN114841929A (en) Board width detection method based on machine vision
CN107552576B (en) A kind of cold coiling machine mandrel spatial position online dimension detection method
CN113884016A (en) Battery piece warping degree detection method
CN103934287A (en) Method for precisely measuring width of steel plate at finish rolling outlet

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