CN108050843B - Heating furnace automatic feeding system based on visible light image and depth image recognition technology - Google Patents
Heating furnace automatic feeding system based on visible light image and depth image recognition technology Download PDFInfo
- Publication number
- CN108050843B CN108050843B CN201711240775.6A CN201711240775A CN108050843B CN 108050843 B CN108050843 B CN 108050843B CN 201711240775 A CN201711240775 A CN 201711240775A CN 108050843 B CN108050843 B CN 108050843B
- Authority
- CN
- China
- Prior art keywords
- steel
- billet
- shifting fork
- signal
- depth
- 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
- F27D3/00—Charging; Discharging; Manipulation of charge
-
- 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
- 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
- F27D3/028—Roller rails or succession of small sized rollers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
- F27D2003/0034—Means for moving, conveying, transporting the charge in the furnace or in the charging facilities
- F27D2003/0046—Means for moving, conveying, transporting the charge in the furnace or in the charging facilities comprising one or more movable arms, e.g. forks
-
- 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
- F27D2019/0028—Regulation
- F27D2019/0059—Regulation involving the control of the conveyor movement, e.g. speed or sequences
Abstract
The automatic heating furnace feeding system based on the visible light image and depth image recognition technology 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 automatic heating furnace feeding system further comprises two depth cameras, two sets of LED light sources, an automatic control unit and a feeding rack electric control system, and the two depth cameras are arranged on two sides of an outlet of the feeding rack; the LED light source is arranged close to the depth of field camera and irradiates the section of the billet in an aligning way; the automatic control unit is connected with the depth-of-field 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. The full-process automation of the heating furnace feeding is realized by adopting a machine vision technology, and particularly, the automatic device is used for replacing the traditional manual operation in the steel billet transportation process from the feeding rack to the conveying roller way so as to improve the production efficiency.
Description
Technical Field
The invention relates to a feeding device and a feeding system for a rod and wire heating furnace in the metallurgical industry, in particular to an automatic feeding system for a heating furnace based on visible light image and depth image recognition technology, which is used between a feeding rack and a conveying roller way of the rod and wire heating furnace.
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 billets to a heating furnace, and mainly comprises a feeding rack, a steel blocking hook, a steel shifting fork and a conveying roller way, wherein during feeding, a plurality of square billets are placed on the feeding rack in rows by a crane, then the steel shifting fork is conveyed with the steel shifting fork by the stepping driving device and the steel blocking hook of the feeding rack one by one according to the production rhythm matching action of the heating furnace, the steel shifting fork places the billets above the conveying roller way, and then the conveying roller way runs to convey the square billets into the heating furnace. At present, the automatic feeding of steel billets from a roller way to a furnace is realized mainly by additionally arranging metal detection elements on two sides of the roller way, but in the current stage, the position of the steel billets and the state of a steel poking fork (information such as whether the steel billets exist on the steel poking fork) need to be observed through human eyes in the transportation process of the steel billets from a feeding rack of the heating furnace to a conveying roller way, then the steel poking fork manually operates a feeding rack driving device to convey the steel billets to the steel poking fork, and then the steel poking fork conveys the steel billets to the conveying roller way. 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.
Disclosure of Invention
The invention aims to solve the technical problem that the existing heating furnace feeding is insufficient, and provides an automatic heating furnace feeding system based on visible light image and depth image recognition technology, so that the full process automation and the unmanned feeding of the heating furnace are realized, and particularly, the automatic device and the technology are used for replacing the traditional manual operation in the steel billet transportation process from a feeding rack to a conveying roller way to improve the production efficiency and reduce the labor cost.
The technical scheme adopted by the invention for solving the technical problems is as follows:
the automatic heating furnace feeding system based on the visible light image and depth image recognition technology 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 automatic heating furnace feeding system further comprises two depth-of-field cameras, two sets of LED light sources, an automatic control unit and a feeding rack electric control system, the two depth-of-field cameras are arranged on two sides of an outlet of the feeding rack and used for shooting visible light images of the sections of the steel billets in the conveying process from the feeding rack to the steel shifting fork, the distance from an object corresponding to each pixel point in the visible light images to a depth-of-field camera is calculated, and a visible light image and a depth image corresponding to the visible light image are output at the same; the two sets of LED light sources are respectively arranged close to one depth of field camera and irradiate aiming at the section of the billet to assist the illumination of the depth of field camera under the dark light condition; the automatic control unit is connected with the depth-of-field 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 module and a communication module, wherein the image processing module is used for triggering the depth camera to shoot at regular time, reading a visible light image and a depth image shot by the depth camera, and analyzing the two images frame by frame; the decision-making module generates action instructions of the feeding rack and the shifting fork according to an analysis result of the image processing module; the communication module sends the action instruction generated by the decision module to the feeding rack electric control system, and the feeding rack electric control system is used for controlling the feeding rack, the steel blocking hook and the steel shifting fork to act (completing corresponding actions of field electric and mechanical equipment) according to the action instruction.
According to the above scheme, the image processing module comprises:
the candidate module is used for performing pre-segmentation on the visible light image by using a brightness segmentation and color segmentation technology, and segmenting a candidate area Rp meeting the preset gray level and color characteristics of the billet from a picture;
the segmentation module is used for carrying out shape matching and filtering on the candidate region Rp by using a shape matching technology, and segmenting a segmentation region Rq meeting the preset billet shape characteristics from a picture;
the billet region calculation module is used for calculating the distance average value M and the variance Std of the region surrounded by Rq on the depth image, limiting the variance Std, wherein the result of the limiting value is S, and removing the region with the distance value smaller than M-2.58S or larger than M +2.58S from the segmentation region Rq to obtain a billet region Rs;
the distance signal calculation module is used for calculating the position of the edge of the cross section of the steel billet closest to the outlet of the feeding rack in the row of steel billets according to the analysis result of the steel billet region Rs and calculating a distance signal P1 from the edge of the cross section of the steel billet to a steel stop hook in the image shot by the two scene depth cameras according to the preset steel stop hook position;
and the billet signal generating module is used for combining the distance signals P1 from the edges of the cross sections of the two billets to the steel stop hook to generate a billet two-end alignment signal S1 and a billet arrival outlet signal S2, and scanning a preset shifting fork area according to the analysis result of the billet area to obtain a billet signal S3 on the shifting fork.
According to the scheme, when the distance signals P1 from the cross section edges of the two steel billets to the steel stopping hook are both smaller than a preset value and the difference between the two signals is smaller than the preset value, the alignment signals S1 at the two ends of the steel billets are generated; and generating a billet arrival outlet signal S2 when the distance signals P1 from the cross section edges of the two billets to the steel stopping hook are both larger than a preset value, wherein the preset value is a deviation value of the alignment of the two ends of the billet.
According to the scheme, the decision module comprises:
the first S3 signal judging module is used for judging whether a steel billet signal S3 is received on the steel shifting fork, if so, a steel shifting command C5 of the steel shifting fork is generated, and the steel shifting fork returns to the conveying roller way after steel is shifted, so that whether a steel billet exists on the steel shifting fork is judged in a circulating manner; if not, generating a forward command C1 of the rack driving device, and driving the billet to move forward by the rack driving device;
the S1 signal judgment module is used for judging whether a billet two-end alignment signal S1 is received or not when the rack driving device drives the billet to move forwards, and if so, a steel blocking hook descending instruction C2 is generated; if not, returning to a forward command C1 of the rack driving device, and continuously driving the billet to move forward by the rack driving device;
the S2 signal judgment module is used for judging whether a steel billet arrival outlet signal S2 is received or not after a steel hook descending instruction C2 is generated, if so, a rack driving device stopping instruction C3 is generated, the driving device stops, the steel billet slides onto the steel shifting fork by means of inertia and self weight, and whether a steel billet signal S3 exists on the steel shifting fork is continuously judged; if not, returning to a steel hook descending command C2;
a second S3 signal judging module, configured to judge whether a steel billet signal S3 is received from the steel shifting fork after the rack driving device stop instruction C3 is generated, if so, it indicates that the steel billet has slipped onto the steel shifting fork, a steel blocking hook lifting instruction C4 is generated, a steel shifting fork steel shifting instruction C5 is generated in a delayed manner, and the S1 signal judging module is returned to judge whether an alignment signal S1 is received from both ends of the steel billet; if not, return is made to generating the gantry drive stop command C3.
According to the scheme, the depth camera adopts a binocular stereo camera, a visible light camera configured with laser scanning or a structured light camera.
According to the scheme, the two scene depth cameras are arranged in parallel to the section of the steel billet.
Compared with the prior art, the invention has the beneficial effects that: the full-process automation and the unmanned feeding of the heating furnace are realized by adopting a machine vision technology to replace human eye observation and matching with a preset equipment action decision scheme, and particularly, the automation device and the technology are used for replacing the traditional manual operation on the billet transportation process from the feeding rack to the conveying roller way so as to improve the production efficiency and reduce the labor cost.
Drawings
FIG. 1 is a layout diagram of an automatic feeding system of a heating furnace based on visible light image and depth image recognition technology;
in FIG. 1, 1-depth of field camera, 2-automatic control unit, 3-feeding bench electronic control system, 4-LED light source, 5-feeding bench, 6-steel retaining hook, 7-steel pulling fork, 8-roller conveyor, 9-steel billet;
FIG. 2 is a system diagram and a work flow diagram of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples.
As shown in figure 1, the automatic heating furnace feeding system based on visible light image and depth image recognition technology comprises a feeding rack 5, a steel blocking hook 6, a steel shifting fork 7 and a conveying roller way 8, wherein the steel blocking hook 6 is arranged on one side of the feeding rack 5, the conveying roller way 8 is used for conveying steel billets 9 from the feeding rack 5 to the steel shifting fork 7, the automatic heating furnace feeding system further comprises two depth-of-field cameras 1, two sets of LED light sources 4, an automatic control unit 2 and a feeding rack electric control system 3, the two depth-of-field cameras 1 are parallel to the section of the steel billets 9 and are arranged on two sides of an outlet of the feeding rack 5, used for shooting the visible light image of the section of the billet 9 in the process of conveying the billet from the feeding rack 5 to the steel shifting fork 7, calculating the distance from an object corresponding to each pixel point in the visible light image to the depth-of-field camera 1, namely simultaneously outputting a visible light image and a depth image corresponding to the visible light image; the two sets of LED light sources 4 are respectively arranged close to one depth of field camera 1 and irradiate aiming at the section of the billet 9, and are used for assisting the illumination of the depth of field camera 1 under the dark light condition; the automatic control unit 2 is connected with the depth of field camera 1 and the feeding rack electric control system 3, and the feeding rack electric control system 3 is connected with the feeding rack 5, the steel blocking hook 6 and the steel shifting fork 7.
The automatic control unit 2 comprises an image processing module, a decision module and a communication module, wherein the image processing module is used for triggering the depth camera 1 to shoot at regular time (the depth camera adopts an industrial camera and can shoot according to a pulse signal sent by the image processing module at regular time), reading a visible light image and a depth image shot by the depth camera 1, and analyzing the two images frame by frame; the decision-making module generates action instructions of all parts of the feeding rack 5, the steel blocking hook 6 and the shifting fork 7 according to the analysis result of the image processing module; the communication module sends the action instruction generated by the decision module to the feeding rack electric control system 3, and the feeding rack electric control system 3 controls the feeding rack 5, the steel blocking hook 6 and the steel shifting fork 7 to act according to the action instruction so as to complete corresponding actions of on-site electric and mechanical equipment.
Two scene depth cameras 1 and two sets of LED light sources 4 are arranged on two sides of an outlet of a feeding rack 5, and an automatic control unit 2 is arranged nearby, so that the two scene depth cameras 1 can provide more abundant information to enable subsequent image segmentation to be more accurate compared with a common visible light camera. The depth camera 1 may adopt a binocular stereo camera, a visible light camera configured with laser scanning, or a structured light camera. The two sets of LED light sources 4 are aligned to the section of the steel billet 9 for irradiation, so that the depth of field camera can still shoot a clear picture under the dark light condition. The automatic control unit 2 is a high-performance computer and a set of automatic control software.
The image processing module is the core of the automatic control unit 2, the image processing module triggers the depth-of-field camera 1 to shoot regularly, and reads the shot visible light image and the shot depth image, then analyzes the two images, and the main task is to segment the steel billet 9 and other background objects from the picture and then provide reliable information guarantee for the decision of the decision module. Before analysis, an ROI (region of interest) region is set by an operator, the ROI region is the largest region of a billet which is possible to appear, and the analysis process is only carried out in the ROI region of an image, so that the identification accuracy is improved, and the identification speed is improved.
As shown in fig. 2, the analysis of the image processing module mainly includes the following steps:
1. adaptively setting a brightness threshold according to the brightness of a picture to realize the first pre-segmentation of the steel billet;
2. the pre-segmentation of the steel billet for the second time is realized according to the color threshold value of the steel billet, the color of the section of the steel billet is observed to be light blue through actual measurement, and the color does not change violently along with the change of illumination, so the steel billet and the background can be distinguished through the color;
3. integrating brightness segmentation and color segmentation to obtain a further candidate area Rp;
4. because the color and brightness threshold values are set widely, Rp contains other background objects besides the steel billet, so that morphological rate filtering and shape matching are further used to remove other backgrounds, and it is ensured that the segmentation result only contains the steel billet, so that a segmentation region Rq is obtained;
5. because the brightness and the color of some background objects are very close to those of the steel billet due to the complex actual field environment, when the background objects are close to or overlapped with the steel billet on a visible light image, the background objects and the steel billet are difficult to separate from the steel billet through brightness and color segmentation, but the distances from the background objects and the steel billet to the camera are generally different greatly, so that the background objects and the steel billet can be separated from each other through the difference of the distances between the background objects and the steel billet; since pre-segmentation is carried out before, most of the segmentation regions Rq are only a few parts of the billet as background objects, the average value M of the segmentation regions Rq on the depth image is the average distance from the end face of the billet to the camera, and the variance Std is caused by the fact that the surface of the billet is uneven, the end faces of the billet cannot be completely aligned and other background objects are included; assuming that the measurement of the distance from the end face of the billet to the camera satisfies the normal distribution, about 99.7% of the results are between M-2.58S, M +2.58S, i.e. most of the pixels representing the billet will be in the interval, and the pixels outside the interval are considered as non-billet background and need to be removed from Rq; the billet is generally arranged on a feeding rack, so Std is not too large, but Std is not too small due to the reason that the surface of the billet is not flat and the end face of the billet cannot be completely aligned, so the Std is limited, the limiting value result is S, and a billet area Rs is obtained after the background of a segmentation area Rq is removed;
6. only one steel billet closest to the outlet of the feeding rack is conveyed to the roller way when the steel billet is conveyed each time, so that only the steel billet closest to the outlet is concerned, and the steel billet closest to the outlet is found by analyzing the position of each region in the Rs;
7. the horizontal position coordinate of the edge of the steel billet section E can be accurately calculated on the image of the steel billet G closest to the outlet of the feeding rack by using an edge searching technology, and the distance P1 from the steel billet to a steel blocking hook can be calculated by comparing the horizontal position coordinate with the preset steel blocking hook horizontal coordinate;
8. because the abrasion of the feeding rack driving device after long-time operation can cause the movement speeds of the two ends of the billet to be different, i.e., one end has moved to the catch and the other end has not yet arrived, if the catch is lowered at this time, one end of the billet can roll down to the shifting fork and the other end can tilt up in the air and can not move continuously, so that the feeding is interrupted, therefore, the steel billet is required to be aligned at two ends and then the steel stopping hook is placed, so that the alignment signal S1 of the two ends of the steel billet is generated according to the distance signal P1 (calculated according to the image segmentation result by P1) from the steel billet cross section edge of the left and right ends (the ends represent the cross section edges of the two ends of the steel billet) of the steel billet to the steel stopping hook shot by the two depth of field cameras, when the P1 of the two ends are both smaller than a preset value (the preset value is a deviation value of the alignment of the two ends of the billet), and the difference between the two is smaller than the preset value, generating a billet two-end alignment signal S1; in addition, when the billet reaches the outlet, the billet can slide onto the shifting fork by means of inertia, at the moment, the feeding rack driving device needs to be immediately stopped, the steel blocking hook needs to be lifted in time to prevent the billet following the steel blocking hook from sliding onto the shifting fork together, and therefore a billet reaching outlet signal S2 needs to be generated according to a P1 signal, namely the billet reaching outlet signal S2 is generated when P1 of two ports are both larger than a preset value;
9. the catch should be raised after the billet has slid down the fork, e.g., premature raising of the catch may cause the catch to hit the falling billet, thus generating a billet signal on the fork when the billet has completely slid down the fork S3.
The decision-making module generates action instructions of each component of the feeding rack and the steel poking fork according to the analysis result of the image processing module, and the specific steps (logic flow) of the decision-making module are shown in fig. 2:
step 3, the rack driving device continues to drive the steel billets, the steel billets continue to move forwards after passing through the position of the steel blocking hook, whether the steel billets reach an outlet signal S2 is judged (when the steel billets reach the outlet of the feeding rack), when the steel billets reach an outlet signal S2, a rack driving device stopping instruction C3 is generated, the feeding rack driving device is stopped, the steel billets immediately behind the rack driving device are guaranteed not to fall down together, the steel billets slide onto the steel shifting fork by means of inertia and dead weight, and the step 4 is carried out; otherwise, the flow returns to the hook lowering command C2 (kept at step 3);
The communication module of the automatic control unit 2 sends the action instruction generated by the decision module to the feeding platform electric control system 3, the general feeding platform electric control system 3 is a PLC system and a matched electric device, an Ethernet communication mode and an OPC communication protocol can be adopted between the communication module and the PLC system, and the feeding platform electric control system 3 completes corresponding actions of field electric and mechanical equipment according to the action instruction.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and all equivalent changes and modifications based on the technical solutions of the present invention should not be excluded from the scope of the present invention.
Claims (3)
1. Heating furnace automatic feeding system based on visible light image and depth image recognition technology, including material loading rack, fender steel hook, group steel fork and rollgang, keep off the steel hook and set up in material loading rack one side, the rollgang is used for transporting the steel billet by the material loading rack and dials steel fork, its characterized in that: the automatic steel billet feeding device comprises a feeding rack, two sets of LED light sources, an automatic control unit and an electric control system of the feeding rack, wherein the two sets of LED light sources are arranged on two sides of an outlet of the feeding rack, and are used for shooting visible light images of the sections of steel billets in the process of conveying the steel billets from the feeding rack to a steel shifting fork, calculating the distance from an object corresponding to each pixel point in the visible light images to the camera, and outputting one visible light image and a depth image corresponding to the visible light image; the two sets of LED light sources are respectively arranged close to one depth of field camera and irradiate aiming at the section of the billet to assist the illumination of the depth of field camera under the dark light condition; the automatic control unit is connected with the depth-of-field 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 module and a communication module, wherein the image processing module is used for triggering the depth camera to shoot at regular time, reading a visible light image and a depth image shot by the depth camera, and analyzing the two images frame by frame; the decision-making module generates action instructions of the feeding rack and the shifting fork according to an analysis result of the image processing module; the communication module sends the action instruction generated by the decision module to the feeding rack electric control system, and the feeding rack electric control system controls the feeding rack, the steel blocking hook and the steel shifting fork to act according to the action instruction;
the image processing module includes:
the candidate module is used for performing pre-segmentation on the visible light image by using a brightness segmentation and color segmentation technology, and segmenting a candidate area Rp meeting the preset gray level and color characteristics of the billet from a picture;
the segmentation module is used for carrying out shape matching and filtering on the candidate region Rp by using a shape matching technology, and segmenting a segmentation region Rq meeting the preset billet shape characteristics from a picture;
the billet region calculation module is used for calculating the distance average value M and the variance Std of the region surrounded by Rq on the depth image, limiting the variance Std, wherein the result of the limiting value is S, and removing the region with the distance value smaller than M-2.58S or larger than M +2.58S from the segmentation region Rq to obtain a billet region Rs;
the distance signal calculation module is used for calculating the position of the edge of the cross section of the steel billet closest to the outlet of the feeding rack in the row of steel billets according to the analysis result of the steel billet region Rs and calculating a distance signal P1 from the edge of the cross section of the steel billet to a steel stop hook in the images shot by the two scene depth cameras according to the preset steel stop hook position;
the billet signal generating module is used for generating a billet two-end alignment signal S1 and a billet arrival outlet signal S2 by combining a distance signal P1 from the edge of the cross section of two billets to the steel stop hook, and scanning a preset steel shifting fork area according to a billet area analysis result to obtain a billet signal S3 on the steel shifting fork; when the distance signals P1 from the cross section edges of the two steel billets to the steel stopping hook are both smaller than a preset value and the difference between the two signals is smaller than the preset value, generating a steel billet two-end alignment signal S1; generating a billet arrival outlet signal S2 when the distance signals P1 from the cross section edges of the two billets to the steel stopping hook are both larger than a preset value, wherein the preset value is an offset value of alignment of the two ends of the billet;
the decision module comprises:
the first S3 signal judging module is used for judging whether a steel billet signal S3 is received on the steel shifting fork, if so, a steel shifting command C5 of the steel shifting fork is generated, and the steel shifting fork returns to the conveying roller way after steel is shifted, so that whether a steel billet exists on the steel shifting fork is judged in a circulating manner; if not, generating a forward command C1 of the rack driving device, and driving the billet to move forward by the rack driving device;
the S1 signal judgment module is used for judging whether a billet two-end alignment signal S1 is received or not when the rack driving device drives the billet to move forwards, and if so, a steel blocking hook descending instruction C2 is generated; if not, returning to a forward command C1 of the rack driving device, and continuously driving the billet to move forward by the rack driving device;
the S2 signal judgment module is used for judging whether a steel billet arrival outlet signal S2 is received or not after a steel hook descending instruction C2 is generated, if so, a rack driving device stopping instruction C3 is generated, the driving device stops, the steel billet slides onto the steel shifting fork by means of inertia and self weight, and whether a steel billet signal S3 exists on the steel shifting fork is continuously judged; if not, returning to a steel hook descending command C2;
a second S3 signal judging module, configured to judge whether a steel billet signal S3 is received from the steel shifting fork after the rack driving device stop instruction C3 is generated, if so, it indicates that the steel billet has slipped onto the steel shifting fork, a steel blocking hook lifting instruction C4 is generated, a steel shifting fork steel shifting instruction C5 is generated in a delayed manner, and the S1 signal judging module is returned to judge whether an alignment signal S1 is received from both ends of the steel billet; if not, return is made to generating the gantry drive stop command C3.
2. The automatic feeding system of the heating furnace based on the visible light image and depth image recognition technology as claimed in claim 1, wherein: the depth camera adopts a binocular stereo camera, a visible light camera configured with laser scanning or a structured light camera.
3. The automatic feeding system of the heating furnace based on the visible light image and depth image recognition technology as claimed in claim 1, wherein: the two scene depth cameras are arranged in parallel to the section of the steel billet.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711240775.6A CN108050843B (en) | 2017-11-30 | 2017-11-30 | Heating furnace automatic feeding system based on visible light image and depth image recognition technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711240775.6A CN108050843B (en) | 2017-11-30 | 2017-11-30 | Heating furnace automatic feeding system based on visible light image and depth image recognition technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108050843A CN108050843A (en) | 2018-05-18 |
| CN108050843B true CN108050843B (en) | 2020-06-19 |
Family
ID=62121251
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711240775.6A Active CN108050843B (en) | 2017-11-30 | 2017-11-30 | Heating furnace automatic feeding system based on visible light image and depth image recognition technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108050843B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111429424B (en) * | 2020-03-20 | 2023-08-11 | 中冶赛迪信息技术(重庆)有限公司 | Heating furnace inlet anomaly identification method based on deep learning |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202594353U (en) * | 2012-05-18 | 2012-12-12 | 浙江中产科技有限公司 | Steel billet detection system for steel billet conveying roller way |
| CN102836886A (en) * | 2011-06-24 | 2012-12-26 | 宝山钢铁股份有限公司 | Detection method of head and tail positions and moving direction of hot-rolled piece |
| 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 |
| JP2017150034A (en) * | 2016-02-24 | 2017-08-31 | Ｊｆｅスチール株式会社 | Apparatus and method for determining discharge flow from refining furnace, and method for refining molten metal |
| CN206674100U (en) * | 2017-02-23 | 2017-11-24 | 首钢京唐钢铁联合有限责任公司 | A kind of monitoring system |
-
2017
- 2017-11-30 CN CN201711240775.6A patent/CN108050843B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102836886A (en) * | 2011-06-24 | 2012-12-26 | 宝山钢铁股份有限公司 | Detection method of head and tail positions and moving direction of hot-rolled piece |
| CN202594353U (en) * | 2012-05-18 | 2012-12-12 | 浙江中产科技有限公司 | Steel billet detection system for steel billet conveying roller way |
| JP2017150034A (en) * | 2016-02-24 | 2017-08-31 | Ｊｆｅスチール株式会社 | Apparatus and method for determining discharge flow from refining furnace, and method for refining molten metal |
| 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 |
| CN206674100U (en) * | 2017-02-23 | 2017-11-24 | 首钢京唐钢铁联合有限责任公司 | A kind of monitoring system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108050843A (en) | 2018-05-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109060827B (en) | Intelligent visual detection and identification equipment | |
| CN112017145B (en) | Efficient automatic slag skimming method and system for molten iron pretreatment | |
| CN208583658U (en) | A kind of metal box-lid automatic code-printing and stamp substandard products automatic reject mechanism | |
| CN103207185A (en) | Steel coil end portion quality detection system and method thereof | |
| CN104764750A (en) | Device and method for automatically detecting quality of elevator balance compensation chain based on machine vision | |
| JP2019108182A (en) | User detection system | |
| CN109052180A (en) | A kind of container automatic aligning method and system based on machine vision | |
| CN109142381B (en) | High-speed visual detection and identification equipment | |
| CN103063167A (en) | Method for judging laser cleaning effect automatically | |
| CN106125246A (en) | A kind of from the method seeking laser focal plane | |
| CN108050843B (en) | Heating furnace automatic feeding system based on visible light image and depth image recognition technology | |
| CN111307812A (en) | Welding spot appearance detection method based on machine vision | |
| KR101272005B1 (en) | Apparatus and method for detecting surface defects of hot billet | |
| CN115384052A (en) | Intelligent laminating machine automatic control system | |
| CN115953726B (en) | Machine vision container face damage detection method and system | |
| CN106379784A (en) | Visual detection method and system for mine reinforcing steel bar inhaul cable | |
| CN116030449B (en) | Automatic sorting method and automatic sorting system for laser cutting pieces | |
| CN108050845A (en) | Heating furnace automatical feeding system based on visible images identification technology | |
| CN108007210A (en) | Heating furnace automatical feeding system based on polyphaser information fusion scheme | |
| CN102556812A (en) | Elevator door auxiliary anti-clamping method and system | |
| CN115436391A (en) | Vehicle oil tank material embryo defect detecting system | |
| CN106404790B (en) | Automatic evaluation system and evaluation method for low-power quality grade of slab | |
| KR20240019361A (en) | Methods, measuring devices, welding systems, and programs for measuring the behavior of welding phenomena | |
| CN115078384A (en) | Quick detection device of stone material large panel surface pit and crack | |
| CN113658135A (en) | Fuzzy PID (proportion integration differentiation) -based self-adaptive dimming belt foreign matter detection method and system |
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 |