CN110044183B - Fang detection automatic feeding method based on machine vision - Google Patents
Fang detection automatic feeding method based on machine vision Download PDFInfo
- Publication number
- CN110044183B CN110044183B CN201910238856.5A CN201910238856A CN110044183B CN 110044183 B CN110044183 B CN 110044183B CN 201910238856 A CN201910238856 A CN 201910238856A CN 110044183 B CN110044183 B CN 110044183B
- Authority
- CN
- China
- Prior art keywords
- machine vision
- billet
- steel
- recognition system
- steel billet
- 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
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F27—FURNACES; KILNS; OVENS; RETORTS
- F27D—DETAILS OR ACCESSORIES OF FURNACES, KILNS, OVENS, OR RETORTS, IN SO FAR AS THEY ARE OF KINDS OCCURRING IN MORE THAN ONE KIND OF FURNACE
- F27D19/00—Arrangements of controlling devices
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F27—FURNACES; KILNS; OVENS; RETORTS
- F27D—DETAILS OR ACCESSORIES OF FURNACES, KILNS, OVENS, OR RETORTS, IN SO FAR AS THEY ARE OF KINDS OCCURRING IN MORE THAN ONE KIND OF FURNACE
- F27D21/00—Arrangements of monitoring devices; Arrangements of safety devices
- F27D21/02—Observation or illuminating devices
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F27—FURNACES; KILNS; OVENS; RETORTS
- F27D—DETAILS OR ACCESSORIES OF FURNACES, KILNS, OVENS, OR RETORTS, IN SO FAR AS THEY ARE OF KINDS OCCURRING IN MORE THAN ONE KIND OF FURNACE
- F27D3/00—Charging; Discharging; Manipulation of charge
- F27D3/02—Skids or tracks for heavy objects
- F27D3/026—Skids or tracks for heavy objects transport or conveyor rolls for furnaces; roller rails
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F27—FURNACES; KILNS; OVENS; RETORTS
- F27D—DETAILS OR ACCESSORIES OF FURNACES, KILNS, OVENS, OR RETORTS, IN SO FAR AS THEY ARE OF KINDS OCCURRING IN MORE THAN ONE KIND OF FURNACE
- F27D19/00—Arrangements of controlling devices
- F27D2019/0003—Monitoring the temperature or a characteristic of the charge and using it as a controlling value
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F27—FURNACES; KILNS; OVENS; RETORTS
- F27D—DETAILS OR ACCESSORIES OF FURNACES, KILNS, OVENS, OR RETORTS, IN SO FAR AS THEY ARE OF KINDS OCCURRING IN MORE THAN ONE KIND OF FURNACE
- F27D21/00—Arrangements of monitoring devices; Arrangements of safety devices
- F27D21/02—Observation or illuminating devices
- F27D2021/026—Observation or illuminating devices using a video installation
Abstract
The utility model provides a take off side and detect automatic feeding method based on machine vision, relates to the mechanical automation field, includes following step: the machine vision recognition system recognizes four coordinates of the outline of the reference object; the machine vision recognition system calculates two blanking points according to the four coordinates of the reference object and determines a horizon; a machine vision recognition system recognizes the end face contour of the steel billet and determines coordinates of four vertexes of the end face; the machine vision recognition system determines whether the contour line segment of the reference object is parallel to the end face contour line segment of the steel billet or not, and judges whether the steel billet is a stripping billet or not; if the machine vision recognition system judges that the steel billet is a billet, the automatic steel billet removing operation can be executed. According to the invention, the method of machine vision is utilized to intelligently identify the stripping billet of the feeding rack, and the identified stripping billet is automatically removed, so that the heating rhythm of the heating furnace can be stabilized, the steel piling risk of a production line is reduced, and the operation rate of the production line is improved.
Description
Technical Field
The invention relates to the field of mechanical automation, in particular to a method for automatically feeding materials by square removal detection based on machine vision.
Background
The steel rolling heating furnace plays an important role in steel enterprises, and the task of the steel rolling heating furnace is to heat steel billets so that the temperature of the steel billets and the temperature distribution of the steel billets meet the rolling requirements. The heating furnace feeding device is a device for conveying steel billets to a heating furnace and mainly comprises a feeding rack, a steel blocking hook, a steel shifting fork and a conveying roller way. In the feeding of blanks, the stripping of the blanks is always an important hidden trouble which influences the heating and production of a heating furnace. Every year, accidents such as steel piling, furnace shutdown and the like in the rolling process caused by square billet stripping directly influence the operational benefits of production enterprises. At present, the cross section shape of a steel billet is mainly observed through human eyes, after a suspected stripping billet is found, cross section diagonal measurement is carried out manually, and when the diagonals are found to be unequal, an operator is informed to manually remove the stripping billet. The whole operation process is mechanically boring, and the manual long-term operation is easy to fatigue to cause operation errors so as to cause faults.
The prior related open technology aiming at the automatic feeding and the square billet stripping detection of the heating furnace comprises the following steps:
the Chinese invention patent application with the patent application number of 201711244182.7, namely 'heating furnace automatic feeding system based on visible light image recognition technology', discloses a feeding system, which comprises a feeding rack, a steel blocking hook, a steel shifting fork and a conveying roller way, wherein the steel blocking hook is arranged on one side of the feeding rack, the conveying roller way is used for conveying steel billets from the feeding rack to the steel shifting fork, the feeding system also comprises two visible light cameras, two sets of LED light sources, an automatic control unit and a feeding rack electric control system, and the visible light cameras are arranged in parallel to the sections of the steel billets and are arranged on two sides of an outlet of the feeding rack; the LED light source is arranged close to the visible light camera and irradiates the section of the billet in alignment; the automatic control unit is connected with the visible light camera and the feeding rack electric control system, and the feeding rack electric control system is connected with the feeding rack, the steel blocking hook and the steel shifting fork; the automatic control unit comprises an image processing module, a decision-making module and a communication module. However, the scheme does not detect the billet blank with the deformed billet shape, once the special-shaped billet enters the furnace, equipment in multiple furnaces may be damaged and influence is caused on production, and unpredictable loss is caused.
The Chinese patent application with the patent application number of 201711326061.7, namely 'double-line automatic steel feeding method of a steel-pushing type heating furnace', discloses an automatic steel feeding method.A hot metal detector is respectively arranged at a steel splitting machine before A, B line shears of the steel-pushing type heating furnace, and whether the previous steel billet enters an A line or a B line is judged according to a signal when the previous steel billet passes through an excitation detection, so that the A, B line controls the steel splitting machine to act; and after the heat detection signal disappears, automatically tapping according to the detected steel feeding requirement of A, B wire steel billets of the steel pushing type heating furnace. The control process of the application is only to judge which line the steel billet enters, and whether the steel billet falls off the square or not and the deformation cannot be judged, so that the influence on the falling off square billet cannot be estimated.
Disclosure of Invention
The invention provides a machine vision-based method for automatically feeding stock by square removal detection, which aims to overcome the problems in the prior art.
The technical scheme adopted by the invention is as follows:
a method for automatically feeding materials through square removal detection based on machine vision comprises the following steps:
(1) feeding the steel billet into a furnace roller way;
(2) the machine vision recognition system recognizes four coordinates of the outline of the reference object in the visual field;
(3) the machine vision recognition system calculates two blanking points according to the four coordinates of the reference object; connecting blanking points and determining a horizon;
(4) a machine vision recognition system recognizes the end face contour of the steel billet and determines coordinates of four vertexes of the end face;
(5) the machine vision recognition system determines whether the contour line segment of the reference object is parallel to the end face contour line segment of the steel billet or not, and judges whether the steel billet is a stripping billet or not;
(6) if the machine vision recognition system judges that the steel billet is normal, the steel billet is conveyed to the next station by the furnace entering roller way in the forward direction; if the machine vision recognition system judges that the steel billet is a billet, the automatic steel billet removing operation can be executed.
Furthermore, the furnace entering roller way, the steel poking fork and the conveying belt are correspondingly controlled by the automatic control system according to the detection result of the machine vision identification system.
Further, in the step (1), the steel billets on the conveying belt are conveyed into a furnace roller way through a steel poking fork.
Further, the machine vision recognition system comprises a server, an upper computer and two cameras arranged on two sides of the furnace entering roller way, wherein the server, the upper computer and the two cameras are connected with each other, and after the cameras acquire images of the reference object and the billet, the upper computer and the server finish the detection and judgment contents from the step (2) to the step (6).
Further, in the step (6), the automatic steel billet removing operation is specifically that the steel billets are reversely conveyed to a steel billet collecting rack in a furnace roller way.
Compared with the prior art, the invention has the advantages that: the invention automatically judges whether the steel billet has the stripping condition or not through the machine vision recognition system, and can automatically recognize the stripping condition of the steel billet under the condition of not influencing production. When judging for taking off the square billet, the system carries out the blank and rejects the operation automatically, can stabilize heating furnace heating rhythm, reduces and produces the line and pile the steel risk, promotes and produces the line operating rate.
Drawings
Fig. 1 is a schematic structural diagram of an automatic feeding system in the invention.
Fig. 2 is a schematic view of the imaging of the camera in the present invention.
FIG. 3 is a schematic flow chart of a feeding method in the present invention.
Detailed Description
The following description of the embodiments of the present invention is provided in connection with the accompanying drawings. Numerous details are set forth below in order to provide a thorough understanding of the present invention, but it will be apparent to those skilled in the art that the present invention may be practiced without these details.
According to the invention, the method of machine vision is utilized to intelligently identify the stripping billet of the feeding rack, and the identified stripping billet is automatically removed, so that the heating rhythm of the heating furnace is stabilized, the steel piling risk of a production line is reduced, and the operation rate of the production line is improved.
The invention mainly comprises a machine vision recognition system and an automatic control system. The machine vision recognition system is used for recognizing whether the steel billet positioned at the front part of the feeding rack has a stripping condition, and if the steel billet has the stripping condition, the automatic control system automatically removes the steel billet. The details are as follows.
In the machine vision recognition system, the parallelism detection of the end face of each fed steel billet is required, and a certain vision error can exist in vision due to the fact that a camera of the machine vision recognition system has a certain vision angle with the end face of the steel billet and a plurality of parallel straight lines on the same plane. For this purpose, it is first necessary to provide a corresponding reference at the billet inspection site for performing the calculation of the visual distance.
As shown in FIG. 1, two cameras 4 on the left and right sides of the furnace run-in table 3 are the camera part of the machine vision recognition system. The camera can identify whether the billet belongs to the desquamated billet or not through a visual identification algorithm by arranging a reference object (an auxiliary steel beam) on the site.
The outline of the reference object (auxiliary steel beam) is square, the reference object and the billet cross section are both within the range of the camera vision, and the reference object (auxiliary steel beam) and the billet cross section are consistent in the depth direction of the camera vision, namely the reference object and the billet cross section are in the same plane.
By using the principle of pinhole imaging, the camera maps parallel straight lines into intersecting straight lines on the image, and the intersection point is called a blanking point. Parallel spatial lines can be considered to intersect at infinity, and the blanking point is the image of this intersection. All horizontal families of parallel lines each intersect at a point at infinity, these points forming an infinite line, which is called the horizon on the image. And if the two blanking points are connected, the connecting line is the horizon. All points on the horizon have one property: all lines drawn from one of its points are parallel to each other.
From the visual field of the camera, the image is shown in FIG. 2, and the AA-BB-CC-DD area is the outline of the reference object. The A-C-D-B area is the outline of the end face of the billet presented by the picture. Since the reference object is known as a square object, the line connecting the two blanking points E, F formed by the two parallel sides of the reference object forms the horizon in the field of view of the camera. At this time, the line segment BA is extended by BA to intersect the horizon, and if the intersection point is point E, the line segment BA is parallel to the line segment DDAA. And similarly, determining whether the line segments AC, CD and DB are respectively parallel to the line segments AABB, BBCC and CCDD, if one condition is not met, determining that the billet is a stripping billet, and executing the operation of automatically removing the billet.
Referring to fig. 1, 2 and 3, the specific processes of the identification and rejection operations are as follows:
(1) the automatic control system controls the steel poking fork 2 to send the steel billet a on the conveying belt 1 into the furnace roller 3.
(2) The machine vision recognition system recognizes four coordinates of the reference object outline within the field of view. Specifically, the camera 4 in the machine vision recognition system transmits the image to the upper computer 5, and the upper computer 5 recognizes four coordinates of the profile of the reference object in the visual field, namely a point AA, a point BB, a point CC and a point DD.
(3) The machine vision recognition system calculates two blanking points according to the four coordinates of the reference object; and connecting the blanking points to determine the horizon. Specifically, the upper computer 5 calculates a blanking point E and a blanking point F from the four coordinates of the reference object, the point AA, the point BB, the point CC, and the point DD, and connects the two blanking points to determine the horizon EF.
(4) And the machine vision recognition system recognizes the end surface profile of the steel billet and determines the coordinates of four vertexes of the end surface. Specifically, a camera 4 in the machine vision recognition system transmits an image to an upper computer 5, the upper computer 5 recognizes the end face contour of the billet, and coordinates of four vertexes of the end face are determined, namely a point A, a point C, a point D and a point B.
(5) The machine vision identification system determines whether the line segment BA is parallel to the line segment DDAA; determining whether line segment AC is parallel to line segment AABB; determining whether the line segment CD is parallel to the line segment BBCC; and determining whether the line segment DB is parallel to the line segment CCDD or not, and judging whether the billet a is a stripping billet or not.
(6) If the machine vision recognition system judges that the billet a is normal, the billet a is conveyed to the next station by the furnace entering roller way 3 in the forward direction; if the machine vision recognition system determines that the billet a is a billet which is taken off, an automatic billet removing operation can be performed, namely, the billet a is reversely conveyed to a billet collecting rack (not shown) by the furnace entering roller 3.
Wherein, the furnace entering roller way 3, the steel shifting fork 2 and the conveyer belt 1 are correspondingly controlled by an automatic control system (not shown in the figure) according to the detection result of the machine vision identification system, and the contents from the step (1) to the step (6) are completed in a matching way.
The above description is only an embodiment of the present invention, but the design concept of the present invention is not limited thereto, and any insubstantial modifications made by using the design concept should fall within the scope of infringing the present invention.
Claims (5)
1. The method for automatically feeding the stock through the stock removal detection based on the machine vision is characterized by comprising the following steps of:
(1) feeding the steel billet into a furnace roller way;
(2) the machine vision recognition system recognizes four coordinates of the outline of the reference object in the visual field;
(3) the machine vision recognition system calculates two blanking points according to the four coordinates of the reference object; connecting blanking points and determining a horizon;
(4) a machine vision recognition system recognizes the end face contour of the steel billet and determines coordinates of four vertexes of the end face;
(5) the machine vision recognition system determines whether the contour line segment of the reference object is parallel to the end face contour line segment of the steel billet or not, and judges whether the steel billet is a stripping billet or not;
(6) if the machine vision recognition system judges that the steel billet is normal, the steel billet is conveyed to the next station by the furnace entering roller way in the forward direction; if the machine vision recognition system judges that the steel billet is a billet, the automatic steel billet removing operation can be executed.
2. The machine vision-based method for automatically feeding stock for square-off detection as claimed in claim 1, wherein: and (2) in the step (1), the steel billets on the conveying belt are conveyed into a furnace roller way through a steel poking fork.
3. The machine vision-based method for automatically feeding stock for square-off detection as claimed in claim 2, wherein: and the furnace entering roller way, the steel poking fork and the conveying belt are correspondingly controlled by the automatic control system according to the detection result of the machine vision identification system.
4. The machine vision-based method for automatically feeding stock for square-off detection as claimed in claim 1, wherein: and the machine vision identification system comprises a server, an upper computer and two cameras arranged on two sides of the furnace entering roller way, which are connected with each other, and after the cameras acquire images of the reference object and the steel billet, the upper computer and the server finish the detection and judgment contents from the step (2) to the step (6).
5. The machine vision-based method for automatically feeding stock for square-off detection as claimed in claim 1, wherein: and (6) automatically removing the steel billets, namely reversely conveying the steel billets to a steel billet collecting rack by a furnace roller way.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910238856.5A CN110044183B (en) | 2019-03-27 | 2019-03-27 | Fang detection automatic feeding method based on machine vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910238856.5A CN110044183B (en) | 2019-03-27 | 2019-03-27 | Fang detection automatic feeding method based on machine vision |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110044183A CN110044183A (en) | 2019-07-23 |
CN110044183B true CN110044183B (en) | 2020-02-07 |
Family
ID=67275306
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910238856.5A Active CN110044183B (en) | 2019-03-27 | 2019-03-27 | Fang detection automatic feeding method based on machine vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110044183B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112053333B (en) * | 2020-08-31 | 2023-04-07 | 中冶赛迪信息技术(重庆)有限公司 | Square billet detection method, system, equipment and medium based on machine vision |
CN112233120B (en) * | 2020-12-16 | 2021-03-16 | 华东交通大学 | Off-square detection method and system based on point cloud data processing |
CN112288746B (en) * | 2020-12-28 | 2021-04-02 | 江苏金恒信息科技股份有限公司 | Machine vision-based off-square detection method and detection system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103714535A (en) * | 2013-12-13 | 2014-04-09 | 大连理工大学 | Binocular vision measurement system camera parameter online adjustment method |
CN206131746U (en) * | 2016-08-31 | 2017-04-26 | 北京佰能电气技术有限公司 | Be applied to steel rolling production line's heating furnace loading attachment |
CN208000053U (en) * | 2017-11-30 | 2018-10-23 | 中冶南方工程技术有限公司 | Heating furnace automatical feeding system based on polyphaser |
CN208155069U (en) * | 2017-11-30 | 2018-11-27 | 中冶南方工程技术有限公司 | Heating furnace automatical feeding system based on visible images |
CN109513639A (en) * | 2019-01-03 | 2019-03-26 | 菲特(天津)智能科技有限公司 | Annular work piece inner wall defect detection device and method based on machine vision |
-
2019
- 2019-03-27 CN CN201910238856.5A patent/CN110044183B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103714535A (en) * | 2013-12-13 | 2014-04-09 | 大连理工大学 | Binocular vision measurement system camera parameter online adjustment method |
CN206131746U (en) * | 2016-08-31 | 2017-04-26 | 北京佰能电气技术有限公司 | Be applied to steel rolling production line's heating furnace loading attachment |
CN208000053U (en) * | 2017-11-30 | 2018-10-23 | 中冶南方工程技术有限公司 | Heating furnace automatical feeding system based on polyphaser |
CN208155069U (en) * | 2017-11-30 | 2018-11-27 | 中冶南方工程技术有限公司 | Heating furnace automatical feeding system based on visible images |
CN109513639A (en) * | 2019-01-03 | 2019-03-26 | 菲特(天津)智能科技有限公司 | Annular work piece inner wall defect detection device and method based on machine vision |
Also Published As
Publication number | Publication date |
---|---|
CN110044183A (en) | 2019-07-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110044183B (en) | Fang detection automatic feeding method based on machine vision | |
CN101986143B (en) | Machine vision belt tear detection and protective device | |
CN104101600B (en) | Cross Section of CC Billet testing of small cracks method | |
CN110480127B (en) | Welding seam tracking system and method based on structured light vision sensing | |
CN106931881A (en) | A kind of polyphaser visible detection method | |
CN103134809A (en) | Welded line defect detection method | |
CN112233120B (en) | Off-square detection method and system based on point cloud data processing | |
JP2007230706A (en) | Vertical split detecting method and device of belt conveyor | |
CN103051872A (en) | Method for detecting conveyor belt deviation based on image edge extraction | |
CN109300125B (en) | Method for extracting pantograph slide plate image of urban rail train in complex environment | |
CN113513991B (en) | Battery pole piece burr height detection method and device | |
CN105784719A (en) | Machine vision inspection terminal capable of sorting goods | |
KR20070006026A (en) | Machine vision system and method for automatic data gathering do hull forming process | |
CN112288746B (en) | Machine vision-based off-square detection method and detection system | |
CN109741311B (en) | Aluminum alloy fusion welding back face fusion width detection method with false edge | |
CN204373688U (en) | A kind of electroplating assembly line outward appearance and dimension control equipment | |
CN111368833A (en) | Full-automatic steel loading method for detecting slab number based on machine vision | |
CN105095897A (en) | Gradient image and similarity weight based digit identification method | |
TW201532695A (en) | Error detection method for detecting a steel strip tail | |
CN210604354U (en) | Cloth pattern and character online acquisition device | |
CN115569994A (en) | Automatic detection system and method for camber of plate blank | |
CN107607539A (en) | A kind of connecting rod is swollen cross section quality vision inspection apparatus and detection method | |
CN209745827U (en) | Curve edge defect detection processing apparatus | |
CN216027967U (en) | Online monitoring and identification system for continuous casting billet rhombus deformation | |
CN115546161A (en) | Method and device for detecting slippage of inlet of rolling mill for rolling steel bars and wires |
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 |