CN115339879B - Intelligent conveying and tracking method and system for small long and square billets based on machine vision - Google Patents

Intelligent conveying and tracking method and system for small long and square billets based on machine vision Download PDF

Info

Publication number
CN115339879B
CN115339879B CN202211276281.4A CN202211276281A CN115339879B CN 115339879 B CN115339879 B CN 115339879B CN 202211276281 A CN202211276281 A CN 202211276281A CN 115339879 B CN115339879 B CN 115339879B
Authority
CN
China
Prior art keywords
billet
conveying
steel
intelligent
machine vision
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
Application number
CN202211276281.4A
Other languages
Chinese (zh)
Other versions
CN115339879A (en
Inventor
彭海波
姚耀春
周容
刘辉
汤占军
赵仕清
朱兴安
齐亮
姜红
马金祥
李伟生
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.)
Kunming University of Science and Technology
Original Assignee
Kunming University of Science and Technology
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 Kunming University of Science and Technology filed Critical Kunming University of Science and Technology
Priority to CN202211276281.4A priority Critical patent/CN115339879B/en
Publication of CN115339879A publication Critical patent/CN115339879A/en
Application granted granted Critical
Publication of CN115339879B publication Critical patent/CN115339879B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
    • B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
    • B65G47/00—Article or material-handling devices associated with conveyors; Methods employing such devices
    • B65G47/74—Feeding, transfer, or discharging devices of particular kinds or types
    • B65G47/82—Rotary or reciprocating members for direct action on articles or materials, e.g. pushers, rakes, shovels
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/20—Image enhancement or restoration by the use of local operators
    • G06T5/30—Erosion or dilatation, e.g. thinning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20036—Morphological image processing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30116—Casting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30136—Metal

Abstract

The invention relates to a machine vision-based intelligent long and small square billet conveying and tracking method and system, and belongs to the technical field of intelligent steel billet conveying and tracking. The method comprises the steps of steel pushing inspection, billet supplementing and steel pushing, conveying tracking, traffic control and stokehole identification. The intelligent conveying device solves the problem of intelligent conveying of long and small square billets of a multi-casting machine to one roller way, and can reduce the cost of high-temperature coating consumables by at least 90% under the condition that the current steel billet heat delivery rate is more than 90%, so that the intelligent conveying device has great significance in energy conservation and consumption reduction; and due to the non-contact property of machine vision, the system fault probability and the operation and maintenance workload are lower, and the method is easy to popularize and apply.

Description

Intelligent conveying and tracking method and system for small long and square billets based on machine vision
Technical Field
The invention belongs to the technical field of intelligent conveying and tracking of steel billets, and relates to a method and a system for intelligently conveying and tracking small long billet billets based on machine vision, in particular to a method and a system for intelligently conveying and tracking small long billet billets based on multiple casting machines and single roller ways based on machine vision.
Background
In order to improve the production efficiency and reduce the production cost, the process from continuous casting, cutting and discharging of steel billets to charging of a heating furnace is an important link, and particularly, how a multi-casting machine realizes orderly and intelligent conveying and tracking of the steel billets, and the process is a research hotspot, and the process reduces the material consumption, the operation and maintenance cost and the workload of manual operation. In the aspect of automatic conveying of steel billets of a single casting machine, the traditional mode can be realized by additionally arranging sensors for weighing, length measuring, positioning and the like and an automatic control system; in the aspect of billet tracking, the traditional mode can be realized by carrying out high-temperature paint code spraying and subsequent visual identification on the end faces of the billets one by one. But the above solution has high one-time investment cost and high production failure rate, and high use cost and operation and maintenance cost of consumables such as paint. In addition, the situation that the automatic conveying of the steel billets is carried out on the multi-casting machine long and small square billets through one roller way at a fast production rhythm is more complex, the conditions of cutting and billet conveying of each casting machine need to be monitored in real time, conveying path planning and traffic control are carried out, otherwise traffic accidents caused by collision of the steel billets of different casting machines are caused, the production rhythm is influenced, and even production or equipment accidents are caused. Therefore, how to overcome the defects of the prior art is a problem to be solved urgently in the technical field of intelligent conveying and tracking of steel billets.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method and a system for intelligently conveying and tracking a long billet and a small billet of a multi-casting machine based on machine vision.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
a machine vision-based intelligent conveying and tracking method for small long and square billets comprises the following steps:
step (1), steel pushing inspection: detecting whether the quantity of the steel billets in each stack position of the steel billet cooling bed reaches a steel billet pushing piece or not by adopting a machine vision algorithm;
step (2), supplementing blanks and pushing steel: calculating the stream number of the billet to be supplemented and the steel pushing starting point position of the steel pusher according to the number of the billets lacking in each stack position and the distribution condition of the billets at the lifting baffle plates on all the runners, and then sending a moving instruction to the steel pusher;
step (3), conveying and tracking: tracking the circulation condition of the steel billet on a conveying roller by adopting a machine vision algorithm, and performing virtual spray number with unique identity for each hot-fed steel billet;
step (4), traffic control: performing path planning and traffic control according to the billet conveying condition in real time by adopting a machine vision algorithm, and sending control signals to corresponding ejection control units and conveying control units to avoid collision of billets;
step (5), furnace front identification: before entering the furnace, the identity of each steel billet is identified and confirmed, the hot-delivery virtual spray number steel billet is tracked by adopting a machine vision algorithm to realize identity identification and confirmation, and the cold-delivery actual spray number steel billet is identified and confirmed by adopting the machine vision algorithm based on a heating furnace front code spraying identification device.
Further, preferably, the method further comprises an offline code spraying step, specifically: and when the steel billets need to be subjected to offline detection or offline stockpiling of the steel billets, unique identity number code spraying is carried out on the offline steel billets.
Further, preferably, in the step (1), an image threshold segmentation machine vision algorithm is adopted for detecting the quantity of the steel billets in each stacking position of the steel billet cooling bed.
Further, in the step (3), it is preferable that the division of the billet body and the background in the transport tracking divides the acquired video signal into individual image frames, and the division of the billet background and the billet body in the image is performed, that is, the RGB color space is converted into the uniform L × a × b space, and the red color (255,0,0) is converted into the uniform L × a × b space
Figure 379256DEST_PATH_IMAGE001
Yellow (255,255,0) converted to->
Figure 944229DEST_PATH_IMAGE002
White (255 ) converted to @>
Figure 124675DEST_PATH_IMAGE003
Let P be a pixel in the converted image and D be the euclidean distance between pixels, the calculation formula is as follows:
Figure 724284DEST_PATH_IMAGE004
；
the segmentation method comprises the following steps:
Figure 597562DEST_PATH_IMAGE005
in the formula (II) when satisfying
Figure 915411DEST_PATH_IMAGE006
When the pixel value of the segmented output result is not satisfied, the pixel value of the current P pixel is maintained, and the value is greater than or equal to ^ R>
Figure 899547DEST_PATH_IMAGE007
When the result of the division output is 0,D PI the color difference value between one pixel of the image after color space conversion and a reference point pixel is obtained; i means a pixel of the image after conversion from RGB color to Lab color, and the pixel has three components, which are ` in `>
Figure 619241DEST_PATH_IMAGE008
Represents the first component of the I pixel, based on the comparison of the value of the first component and the value of the first component>
Figure 663421DEST_PATH_IMAGE009
；/>
Figure 202987DEST_PATH_IMAGE010
Represents a second component of the I pixel, and +>
Figure 990814DEST_PATH_IMAGE011
；/>
Figure 565015DEST_PATH_IMAGE012
Represents a third component of an I pixel, based on the sum of the values of the pixels in the image signal and the pixel signal>
Figure 780095DEST_PATH_IMAGE013
；P L Representing the first component of the P pixels in the converted image, P a A second component representing P pixels in the converted image, P b A third component representing a P pixel in the converted image; t is a threshold value for controlling the similarity; will->
Figure 806957DEST_PATH_IMAGE014
The other part is divided as a billet background to realize billet conveying tracking.
Further, in the step (4), during traffic control, the judgment that the steel billet is in place before the turntable rotates is to judge whether the steel billet reaches a specified position by a machine vision algorithm, wherein the specified position comprises a preset front end position and a preset rear end position, the position of the steel billet is required to be between the front end position and the rear end position, and then the rotation is started.
Further, preferably, in the step (5), the identity recognition of the cold-fed actual spray-number steel billet is confirmed by adopting an image threshold segmentation machine vision algorithm based on a spray-code recognition device in front of the heating furnace.
The invention also provides a machine vision-based intelligent long billet conveying and tracking system, which adopts the machine vision-based intelligent long billet conveying and tracking method, comprises a billet discharging control unit and a conveying control unit, and is characterized by further comprising the following steps:
the system comprises an industrial video machine vision system, an intelligent blank discharging subsystem, an intelligent conveying subsystem, a billboard display system and a robot code spraying system;
the industrial video machine vision system is respectively connected with the intelligent blank discharging subsystem, the intelligent conveying subsystem, the billboard display system and the robot code spraying system;
the intelligent ejection subsystem is respectively connected with the ejection control unit and the billboard display system;
the intelligent conveying subsystem is respectively connected with the conveying control unit and the billboard display system;
the industrial video machine vision system is used for identifying the position, the length and the identity of the steel billet, respectively transmitting the identification result to the intelligent billet discharging subsystem and the intelligent conveying subsystem, and also used for carrying out virtual number spraying with unique identity for each hot-conveying steel billet;
the intelligent ejection subsystem is used for transmitting baffle lifting and steel pusher movement control signals of steel billet ejection to the ejection control unit for execution according to the position, length and identity information of the steel billet transmitted by the industrial video machine vision system;
the intelligent conveying subsystem is used for transmitting conveying start, stop and rotation signals of a steel billet roller way to the conveying control unit to be executed according to the position, length and identity information of the steel billet transmitted by the industrial video machine vision system;
the billboard display system is used for displaying the conditions of the full-flow billet ejection and conveying identified and operated by the industrial video machine vision system, the intelligent ejection subsystem and the intelligent conveying subsystem;
the robot code spraying system is used for carrying out unique identity code spraying on off-line steel billets, and when code spraying is carried out, virtual spray codes of the steel billets are obtained from an industrial video machine vision system for code spraying;
the ejection control unit is used for ejecting steel billets from the casting machine, the action execution control command signals of the lifting of the baffle and the movement of the pusher are from the intelligent ejection subsystem, and the execution results are fed back to the intelligent ejection subsystem after the action execution is finished;
the conveying control unit is used for conveying roller way steel billets, control signals of starting, stopping and rotating of roller way conveying are from the intelligent conveying subsystem, and execution results are fed back to the intelligent conveying subsystem after actions are executed.
Further, preferably, the industrial video machine vision system comprises a plurality of industrial cameras, and the installation positions of the industrial cameras comprise a steel billet cooling bed, a steel moving roller way, a conveying turntable and the upper part of the conveying roller way.
Further, preferably, the billboard display system adopts a digital twin visualization mode to provide real-time operation conditions for a production line worker monitoring system, and displays real-time position conditions of steel billets identified by the industrial video machine vision system, billet ejection conditions of a casting machine of the intelligent ejection subsystem, and billet roller conveying conditions of the intelligent conveying subsystem.
The virtual spray number corresponds to the actual spray number, and the only digital identity number is carried out on the hot-fed steel billet according to the existing normal actual spray number rule; the machine vision algorithm is used for tracking the circulation condition of the steel billets on the conveying roller way, and the digital serial number generated by each steel billet virtual spray mark is visually displayed to a user in real time in a digital twin mode, namely the virtual spray mark is obtained. When the billets need to be subjected to offline detection or stockpiled, actual code spraying is carried out on the offline billets according to the unique digital identity numbers generated by the virtual spray numbers by utilizing conventional physical spray numbers such as conventional high-temperature coatings or aluminum wires.
Compared with the prior art, the invention has the following beneficial effects:
the invention solves the problem of intelligent conveying of the small long billet to one roller way of the multi-casting machine, and compared with the prior related technology which realizes automatic conveying of the billet or realizes tracking by physically spraying codes on the billet one by means of various sensors, the invention has low one-time investment cost; and because the hot-conveying steel billet only carries out virtual number spraying, namely the higher the hot-conveying rate is, the lower the average number spraying cost of the steel billet is. Under the condition that the hot delivery rate of the current steel billet mostly exceeds 90 percent, the invention can reduce the cost of high-temperature coating consumables by at least 90 percent, and has great significance for energy conservation and consumption reduction; and due to the non-contact property of machine vision, the system fault probability and the operation and maintenance workload are lower.
Drawings
FIG. 1 is a schematic structural diagram of a long billet and small billet intelligent conveying and tracking system based on machine vision;
FIG. 2 is a flow chart of slab supplementing and steel pushing of the present invention;
FIG. 3 is a schematic diagram illustrating the judgment of the steel billet in place before the turntable rotates during traffic control according to the present invention; wherein, (a) is a calibration schematic diagram, and (b) is a billet schematic diagram;
FIG. 4 is a diagram illustrating a physical layout of an exemplary application of the present invention;
FIG. 5 is a schematic representation of the stokehold identification of the present invention;
wherein: the method comprises the following steps of 1-ejection control unit, 2-conveying control unit, 3-industrial video and visual system thereof, 4-intelligent ejection subsystem, 5-intelligent conveying subsystem, 6-billboard display system and 7-robot code spraying system.
Detailed Description
The present invention will be described in further detail with reference to examples.
It will be appreciated by those skilled in the art that the following examples are illustrative of the invention only and should not be taken as limiting the scope of the invention. The examples do not specify particular techniques or conditions, and are performed according to the techniques or conditions described in the literature in the art or according to the product specifications. The materials or equipment used are not indicated by manufacturers, and all are conventional products available by purchase.
Example 1
A machine vision-based intelligent conveying and tracking method for small long and square billets comprises the following steps:
step (1), steel pushing inspection: detecting whether the quantity of the steel billets in each stack position of the steel billet cooling bed reaches a steel billet pushing component or not by adopting a machine vision algorithm;
step (2), blank supplementing and steel pushing: calculating the stream number of the billet to be supplemented and the steel pushing starting point position of the steel pusher according to the number of the billets lacking in each stack position and the distribution condition of the billets at the lifting baffle plates on all the runners, and then sending a moving instruction to the steel pusher;
for example, if the number of the steel billets at the stacking position is 4, if only 3 steel billets at the current stacking position lack 1 steel billet, and the second flow has 1 steel billet, the pusher starts to push steel from the second flow;
step (3), conveying and tracking: tracking the circulation condition of the steel billet on a conveying roller by adopting a machine vision algorithm, and performing virtual spray number with unique identity for each hot-fed steel billet;
step (4), traffic control: performing path planning and traffic control according to the steel billet conveying condition in real time by adopting a machine vision algorithm, and sending control signals to the corresponding ejection control unit and the corresponding conveying control unit to avoid collision of the steel billets;
step (5), furnace front identification: before entering a furnace, the identity of each steel billet is identified and confirmed, the hot-delivery virtual spray number steel billet is tracked by adopting a machine vision algorithm to realize identity identification and confirmation, and the cold-delivery actual spray number steel billet is identified and confirmed by adopting the machine vision algorithm based on a heating stokehole code spraying identification device.
The invention does not limit the adopted machine vision algorithm, for example, euclidean image segmentation method and morphology are adopted;
the method also comprises a step of off-line code spraying, which specifically comprises the following steps: and when the steel billets need to be subjected to offline detection or offline stacking, carrying out unique identity number code spraying on the offline steel billets.
In the step (1), an image threshold segmentation machine vision algorithm is adopted for detecting the quantity of the steel billets in each stacking position of the steel billet cooling bed.
In the step (3), during the conveying and tracking, the division of the billet body and the background divides the collected video signal into separate image frames, and divides the billet background and the billet body in the images, namely, the RGB color space is converted into a uniform L a b space, and the red color 255,0,0 is converted into the image frame
Figure 398476DEST_PATH_IMAGE015
Yellow 255,255,0 converted to->
Figure 827183DEST_PATH_IMAGE016
Based on the conversion of white 255,255,255 into { } based on }>
Figure 213165DEST_PATH_IMAGE017
Let P be a pixel in the converted image and D be the euclidean distance between pixels, the calculation formula is as follows:
Figure 992902DEST_PATH_IMAGE018
；
the segmentation method comprises the following steps:
Figure 122532DEST_PATH_IMAGE019
in the formula (II) when satisfying
Figure 405746DEST_PATH_IMAGE020
When the pixel value of the segmented output result is not satisfied, the pixel value of the current P pixel is maintained, and the value is greater than or equal to ^ R>
Figure 228208DEST_PATH_IMAGE021
When the result of the division output is 0,D PI the color difference value between one pixel of the image after color space conversion and a reference point pixel is obtained; i means a pixel of the image after conversion from RGB color to Lab color, and the pixel has three components, which are ` in `>
Figure 964083DEST_PATH_IMAGE022
Represents the first component of the I pixel, based on the comparison of the value of the first component and the value of the first component>
Figure 897404DEST_PATH_IMAGE023
；/>
Figure 300704DEST_PATH_IMAGE024
Represents a second component of the I pixel, and +>
Figure 25559DEST_PATH_IMAGE025
；/>
Figure 248730DEST_PATH_IMAGE026
Represents the third component of the I pixel, based on the comparison result>
Figure 985741DEST_PATH_IMAGE027
；P L Representing the first component of the P pixels in the converted image, P a Second one representing P pixels in the converted imageComponent, P b A third component representing a P pixel in the converted image; t is a threshold value for controlling the similarity; will->
Figure 243547DEST_PATH_IMAGE028
The other part is divided as a billet background to realize billet conveying tracking.
In the step (4), during traffic control, the judgment that the steel billet is in place before the turntable rotates is to judge whether the steel billet reaches a specified position by a machine vision algorithm, wherein the specified position comprises a preset front end position and a preset rear end position, the position of the steel billet is required to be between the front end position and the rear end position, and then the steel billet starts to rotate.
And (5) carrying out identity recognition and confirmation on the cold-fed actual spray number steel billet by adopting an image threshold segmentation machine vision algorithm based on a heating stokehole spray code recognition device.
In the invention, the default of the initial value T is 100, and a proper numerical value can be debugged and set according to the actual conditions of light and environment in different areas on site.
The invention also provides a machine vision-based intelligent long billet conveying and tracking system, which adopts the machine vision-based intelligent long billet conveying and tracking method, comprises a billet discharging control unit 1 and a conveying control unit 2, and is characterized by further comprising the following steps:
an industrial video machine vision system 3, an intelligent blank discharging subsystem 4, an intelligent conveying subsystem 5, a billboard display system 6 and a robot code spraying system 7, as shown in figure 1;
the industrial video machine vision system 3 is respectively connected with the intelligent blank discharging subsystem 4, the intelligent conveying subsystem 5, the billboard display system 6 and the robot code spraying system 7;
the intelligent ejection subsystem 4 is respectively connected with the ejection control unit 1 and the billboard display system 6;
the intelligent conveying subsystem 5 is respectively connected with the conveying control unit 2 and the billboard display system 6;
the industrial video machine vision system 3 is used for identifying the position, the length and the identity of the steel billet, respectively transmitting the identification result to the intelligent ejection subsystem 4 and the intelligent conveying subsystem 5, and also used for carrying out virtual number spraying with unique identity for each hot-conveying steel billet;
the intelligent ejection subsystem 4 is used for transmitting baffle lifting and pusher movement control signals of billet ejection to the ejection control unit 1 for execution according to the position, length and identity information of the billets transmitted by the industrial video machine vision system 3;
the intelligent conveying subsystem 5 is used for transmitting the conveying start/stop and rotation signals of the billet roller way to the conveying control unit 2 for execution according to the position, length and identity information of the billet transmitted by the industrial video machine vision system 3;
the billboard display system 6 is used for displaying the conditions of the full-flow billet ejection and conveying identified and operated by the industrial video machine vision system 3, the intelligent ejection subsystem 4 and the intelligent conveying subsystem 5;
the robot code spraying system 7 is used for carrying out unique identity code spraying on off-line steel billets, and when code spraying is carried out, virtual spray codes of the steel billets are obtained from the industrial video machine vision system 3 and code spraying is carried out;
the ejection control unit 1 is used for ejecting steel billets from the casting machine, the action execution control command signals of baffle lifting and steel pusher moving are from the intelligent ejection subsystem 4, and the execution result is fed back to the intelligent ejection subsystem 4 after the action execution is finished;
the conveying control unit 2 is used for conveying roller way steel billets, control signals for starting, stopping and rotating the roller way conveying are from the intelligent conveying subsystem 5, and execution results are fed back to the intelligent conveying subsystem 5 after actions are executed.
The industrial video machine vision system 3 comprises a plurality of industrial cameras, and the installation positions of the industrial cameras comprise a steel billet cooling bed, a steel moving roller way, a conveying turntable and the upper part of the conveying roller way.
The billboard display system 6 adopts a digital twin visual mode to provide real-time operation conditions for a production line worker monitoring system, and displays the real-time position conditions of the steel billets identified by the industrial video machine vision system 3, the steel billet ejection conditions of the casting machine of the intelligent ejection subsystem 4 and the steel billet roller way conveying conditions of the intelligent conveying subsystem 5.
Example 2
The machine vision-based intelligent conveying and tracking method for the long and small square billets of the multi-casting machine comprises the following steps of: push away the steel inspection, mend the base and push away the steel, the off-line spouts a yard, carries tracking, traffic control, stokehold discernment specifically is:
and (3) steel pushing inspection: detecting whether the quantity of the steel billets in each stack position of the steel billet cooling bed reaches a steel billet pushing piece or not by adopting a machine vision algorithm;
b, blank supplementing and steel pushing: calculating the flow number of the billet to be supplemented and the steel pushing starting point position of the steel pusher according to the quantity of the billets lacking in each stack position and the distribution condition of the billets at the lifting baffle plates on all the runners, and then sending a moving instruction to the steel pusher;
and (5) offline code spraying: when the steel billets cannot be eaten by the heating furnace due to the quality problem and the off-line detection is needed or other reasons cause the steel billets to be conveyed, and the steel billets need to be stocked off-line, unique identity number code spraying is carried out on the off-line steel billets;
conveying and tracking: tracking the circulation condition of the steel billets on a conveying roller way by adopting a machine vision algorithm, and performing virtual spraying with unique identity for each hot-fed steel billet (only the steel billet which is off-line is actually sprayed);
traffic control: performing path planning and traffic control according to the billet conveying condition in real time by adopting a machine vision algorithm, and sending control signals to corresponding ejection control units and conveying control units to avoid traffic accidents such as collision of billets and the like;
furnace front identification: before entering the furnace, the identity of each steel billet is identified and confirmed, the hot-delivery virtual spray number steel billet realizes the identity identification and confirmation by means of the online full-flow industrial camera machine vision tracking, and the cold-delivery actual spray number steel billet realizes the identity identification and confirmation by means of the heating furnace front code spraying recognition device machine vision.
A long billet intelligent conveying and tracking system based on machine vision comprises: the device comprises a blank ejection control unit 1, a conveying control unit 2, an industrial video machine vision system 3, an intelligent blank ejection subsystem 4, an intelligent conveying subsystem 5, a billboard display system 6 and a robot code spraying system 7.
The ejection control unit 1 and the conveying control unit 2 are self-provided industrial control systems for ejection and roller conveying of the original casting machine, and adaptive transformation is carried out;
the industrial video machine vision system 3 comprises a plurality of industrial cameras (preferably, one industrial camera is mounted every 10 meters) mounted along the full process of a steel billet cooling bed, a steel moving roller way, a conveying turntable and a conveying roller way, and is used for identifying the position, the length and the identity of a steel billet and respectively informing the related results to the intelligent knockout subsystem 4 and the intelligent conveying subsystem 5;
the intelligent ejection subsystem 4 and the intelligent conveying subsystem 5 are intelligent subsystems which respectively correspond to ejection and conveying of steel billets;
the billboard display system 6 is responsible for displaying the conditions of all-flow billet ejection and conveying identified and operated by the industrial video machine vision system 3, the intelligent ejection subsystem 4 and the intelligent conveying subsystem 5, and the real-time operation condition of the production line employee monitoring system is provided in a digital twin visualization mode;
and the robot code spraying system 7 is responsible for carrying out unique identity code spraying on off-line steel billets.
Examples of applications
A machine vision-based intelligent conveying and tracking method for long and small square billets of a multi-casting machine is mainly characterized by comprising the following steps as shown in figure 4: steel pushing inspection, blank supplementing and steel pushing, offline code spraying, conveying tracking, traffic control and stokehole identification. Wherein the steel pushing inspection, the slab supplementing and the steel pushing are shown in a figure 2 of a slab supplementing and steel pushing process diagram.
In FIG. 4, A1# -E4 # are all industrial cameras; the industrial camera and each tracking main body jointly form an industrial video machine vision system; the automatic ejection main machines 1# and 2# belong to an ejection subsystem 4; the continuous casting machine, the cooling bed, the PLC, the roller way and the like are pre-transformation equipment or systems and belong to a knockout control unit or a conveying control unit.
And the steel pushing inspection is carried out, whether the quantity of the steel billets in each stack position of the steel billet cooling bed meets the steel pushing condition is detected by machine vision, and the steel billet pushing inspection is shown in an industrial camera A1#, an industrial camera A2#, an industrial camera A3#, an industrial camera A4# or an industrial camera B1#, an industrial camera B2#, an industrial camera B3# and an industrial camera B4#.
And the blank supplementing and steel pushing are carried out. And calculating the stream number of the billet to be supplemented and the steel pushing starting position of the steel pusher according to the quantity of the billet lacking in each stack position and the distribution condition of the billet at the lifting baffle on all the runners, and sending an instruction for opening the lifting baffle for the stream to be supplemented. The billet enters the knockout roller way through the lifting baffle. And after the steel billet completely leaves the lifting baffle area, closing the lifting baffle, and then sending a moving instruction to the pusher, which is shown in a steel moving area of FIG. 4.
And printing codes on the lower line. When the steel billets need offline detection due to quality problems or the heating furnace cannot eat hot steel billets due to other reasons (such as a fault of a rolling mill), and the steel billets need to be offline and stacked, a code spraying robot installed at the offline position of the cooling bed is responsible for carrying out unique identity code spraying on the offline steel billets, and the figure of the cooling bed area is 4.
And the conveying is tracked. The machine vision full-flow tracking method of the industrial cameras additionally arranged along the conveying roller way tracks the flowing condition of the steel billets on the conveying roller way, and performs virtual number spraying of unique identity for each hot-conveying steel billet (only the steel billet which is off line actually performs number spraying), and the method is shown in all roller way conveying parts of fig. 4.
The traffic control is described. Setting a timestamp for the steel billet of each stream arriving at a steel pushing area according to the pulling speed of a casting machine in real time, estimating the arrival time of each stream of subsequent steel billets, sequencing the fastest arriving flow channels and the slowest arriving flow channels, and automatically deducing the billet delivery efficiency of all conditions by a system according to a traffic light model taking unblocked steel billets and minimum temperature drop as targets according to the conveying condition of the steel billets on a roller way to carry out path planning and traffic control (note: the model firstly aims at unblocking the steel billet on the roller way, and then conveys the steel billet as soon as possible by taking minimum temperature drop and energy consumption reduction as targets), thereby avoiding traffic accidents such as collision of the steel billets. As shown in fig. 4, when the # 2 turntable is automatically conveying the # 2 continuous casting machine billet, the roller way between the # 1 turntable and the # 2 turntable is in a conveying stop state; when the No. 2 turntable is in a horizontal state and can convey the steel billets of the No. 3 continuous casting machine, the roller way between the No. 1 turntable and the No. 2 turntable automatically conveys the steel billets to the No. 2 turntable, and after the machine visually judges that the steel billets are completely parked in place on the No. 2 turntable, a 90-degree rotation command is sent to the No. 2 turntable, and then the steel billets are automatically conveyed to the heating furnace.
And identifying the furnace front. Before entering the furnace, the identity of each steel billet is identified and confirmed, and the hot-delivery virtual spray number steel billet realizes identity identification and confirmation by means of online full-flow industrial camera machine vision tracking; the cold-conveying actual number-spraying steel billet realizes identity recognition and confirmation by means of machine vision of a code spraying recognition device in front of a heating furnace, as shown in figure 5.
The number of the steel billets is realized by adopting an image threshold segmentation machine vision algorithm, namely, the image gray scale is divided into different levels, and then a method for setting a gray scale threshold (threshold) is used for determining a meaningful area or a boundary of a segmentation object. When the brightness difference between the target billet and the background object in the image is smaller, the double-peak characteristic of the image gray level histogram observed from the histogram is not obvious, and a proper threshold value is not easy to determine by directly using the histogram, so that a discriminant analysis method for calculating 0-order moment and 1-order moment of the histogram is used for determining the optimal threshold value.
Setting the total pixel number of the image as N and the gray value as i
Figure 142233DEST_PATH_IMAGE029
Then, the 0-order matrix and the 1-order matrix of the gray distribution with the gray level K are respectively defined as follows:
the 0 th moment is:
Figure 118280DEST_PATH_IMAGE030
the 1 st order moment is: />
Figure 393403DEST_PATH_IMAGE031
。
When K = L-1, the signal is transmitted,
Figure 505716DEST_PATH_IMAGE032
wherein L is the image gray level, and L-1 is the maximum value thereof; />
Figure 840882DEST_PATH_IMAGE033
In which>
Figure 38645DEST_PATH_IMAGE034
Is the average gray value of the image. L-1 representsThe maximum value when the image gray level is L, for example, the image gray level L is 256, and the value range is 0 to 255.
Let M-1 thresholds of the image be:
Figure 117460DEST_PATH_IMAGE035
divide the image into classes of M gray values->
Figure 349858DEST_PATH_IMAGE036
And &>
Figure 590346DEST_PATH_IMAGE037
Then each type is based on>
Figure 540985DEST_PATH_IMAGE038
The occurrence probability of (a) is: />
Figure 157911DEST_PATH_IMAGE039
And the corresponding probability averages are: />
Figure 244816DEST_PATH_IMAGE040
，（/>
Figure 656205DEST_PATH_IMAGE041
) Therefore, the inter-class variance of each class can be obtained as: />
Figure 828561DEST_PATH_IMAGE042
In the handle type>
Figure 249178DEST_PATH_IMAGE043
Threshold value set which has the greatest value->
Figure 190589DEST_PATH_IMAGE044
As the optimal set of thresholds for M-valuing. When the classification is made into 2 classes, that is, when M is 2, a threshold value for binarization can be obtained.
The judgment of the in-place of the steel billet before the rotation of the turntable is to judge whether the steel billet reaches the designated position through machine vision, the judgment comprises a front position and a rear position, the steel billet is required not to exceed the front end and the rear end of the position, the rotation is started when the steel billet is just positioned between the designated positions, mark positions A and B are arranged in a template image, and as shown in figure 3, the judgment is realized by adopting image segmentation and a morphological post-processing machine vision algorithm.
During the tracking of the billet in the roller conveying process, the division of the body and the background divides the collected video signal into separate image frames, and divides the billet background and the billet body in the image, namely, the RGB color space is converted into the uniform L a b space, and the color is recorded into the color of red (255,0,0) after being converted into the color of the uniform L a b space
Figure 38459DEST_PATH_IMAGE045
Yellow (255,255,0) converted into->
Figure 698111DEST_PATH_IMAGE046
White (255 ) convert into->
Figure 656839DEST_PATH_IMAGE047
Let P be a pixel in the converted image and D be the Euclidean distance between pixels, based on the formula >>
Figure 718336DEST_PATH_IMAGE048
Then, the segmentation strategy is:
Figure 737108DEST_PATH_IMAGE049
the meaning in the formula is that when the condition is satisfied, the pixel value of the segmentation output result keeps the pixel value of the current P pixel, and when the condition is not satisfied, the segmentation output result is 0, and the DPI refers to the color difference value between one pixel of the image after color space conversion and the pixel of the reference point; i refers to a pixel of an image converted from RGB to Lab color, the pixel having three components: (
Figure 618476DEST_PATH_IMAGE050
Represents the first component of an I pixel, and>
Figure 380896DEST_PATH_IMAGE051
；/>
Figure 31320DEST_PATH_IMAGE052
represents the second component of the I pixel, is selected>
Figure 220993DEST_PATH_IMAGE053
；/>
Figure 120816DEST_PATH_IMAGE054
Represents the third component of the I pixel, based on the comparison result>
Figure 155768DEST_PATH_IMAGE055
；P L Representing the first component of P pixels in the converted image, P a A second component representing P pixels in the converted image, P b The third component representing P pixels in the converted image), T is a threshold for controlling the similarity. Will->
Figure 923348DEST_PATH_IMAGE056
The other part of the steel billet is divided as a billet body, and the billet conveying tracking is realized by taking the other part as a billet background.
A billet intelligent conveying tracking system based on machine vision mainly comprises a billet discharging control unit 1, a conveying control unit 2, an industrial video machine vision system 3, an intelligent billet discharging subsystem 4, an intelligent conveying subsystem 5, a billboard display system 6 and a robot code spraying system 7 as shown in figure 1.
The ejection control unit 1 and the conveying control unit 2 are self-provided industrial control systems for ejection and roller conveying of the original casting machine, and can be subjected to adaptive transformation, such as an automatic ejection and automatic conveying main machine shown in fig. 4.
The industrial video machine vision system 3 comprises a plurality of industrial cameras which are arranged along the whole process of a steel billet cooling bed, a steel moving roller way, a conveying turntable and a conveying roller way, wherein 1 industrial camera is arranged on the average per 10 meters and used for identifying the position, the length and the identity of a steel billet and informing the related results to the intelligent ejection subsystem 4 and the intelligent conveying subsystem 5 respectively;
the intelligent ejection subsystem 4 and the intelligent conveying subsystem 5 are intelligent subsystems which respectively correspond to ejection and conveying of steel billets;
the billboard display system 6 is responsible for displaying the conditions of all-process billet ejection and conveying identified and operated by the industrial video machine vision system 3, the intelligent ejection subsystem 4 and the intelligent conveying subsystem 5, and the real-time operation condition of the production line employee monitoring system is provided in a digital twin visual mode;
and the robot code spraying system 7 is responsible for carrying out unique identity code spraying on off-line steel billets.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.

Claims (7)

1. A long material small square billet intelligent conveying and tracking method based on machine vision is characterized by comprising the following steps:
step (1), steel pushing inspection: detecting whether the quantity of the steel billets in each stack position of the steel billet cooling bed reaches a steel billet pushing component or not by adopting a machine vision algorithm;
step (2), supplementing blanks and pushing steel: calculating the flow number of the billet to be supplemented and the steel pushing starting point position of the steel pusher according to the quantity of the billets lacking in each stack position and the distribution condition of the billets at the lifting baffle plates on all the runners, and then sending a moving instruction to the steel pusher;
step (3), conveying and tracking: tracking the circulation condition of the steel billet on a conveying roller by adopting a machine vision algorithm, and performing virtual spray number with unique identity for each hot-fed steel billet;
step (4), traffic control: performing path planning and traffic control according to the steel billet conveying condition in real time by adopting a machine vision algorithm, and sending control signals to the corresponding ejection control unit and the corresponding conveying control unit to avoid collision of the steel billets;
step (5), furnace front identification: before entering a furnace, the identity of each steel billet is identified and confirmed, the hot-delivery virtual spray number steel billet is tracked by adopting a machine vision algorithm to realize identity identification and confirmation, and the cold-delivery actual spray number steel billet is identified and confirmed by adopting a machine vision algorithm based on a heating furnace front spray code identification device;
still include off line and spout a yard step, specifically do: when the steel billets need to be subjected to offline detection or stockpiled, unique identity number code spraying is carried out on the offline steel billets;
in the step (4), during traffic control, the judgment that the steel billet is in place before the turntable rotates judges whether the steel billet reaches the specified position through a machine vision algorithm, wherein the specified position comprises a preset front end position and a preset rear end position, the steel billet is required to be positioned between the front end position and the rear end position, and then the steel billet starts to rotate;
the virtual spray number corresponds to the actual spray number, and the hot-fed steel billet is subjected to unique digital identity numbering according to the existing normal actual spray number rule; the method comprises the steps that the circulation condition of steel billets on a conveying roller way is tracked through a machine vision algorithm, the number generated by each steel billet virtual spray number is visually displayed to a user in a digital twin mode, namely the virtual spray number is obtained, and when the steel billets need to be subjected to offline detection or offline stacking of the steel billets is needed, actual code spraying is carried out on the offline steel billets according to the unique number identity generated by the virtual spray number by using an entity spray number.
2. The intelligent long billet conveying and tracking method based on machine vision as claimed in claim 1, wherein in the step (1), an image threshold segmentation machine vision algorithm is adopted for detecting the number of the billets in each stacking position of the billet cooling bed.
3. The intelligent transportation tracking method for long and small billet based on machine vision as claimed in claim 1, wherein in the step (3), during transportation tracking, the segmentation of the billet body and the background is to segment the collected video signal into individual video signalsImage frame, dividing the billet background and billet body in the image, namely converting RGB color space into uniform L a b space, converting red (255,0,0) into R Lab Yellow (255,255,0) converted to Y Lab White (255 ) is converted to W Lab Let P be a pixel in the converted image and D be the euclidean distance between pixels, the calculation formula is as follows:
Figure FDA0004034327890000021
the segmentation method comprises the following steps:
Figure FDA0004034327890000022
in the formula (II) when satisfying
Figure FDA0004034327890000023
When the pixel value of the segmented output result holds the pixel value of the current P pixel, and when not satisfied ^ er>
Figure FDA0004034327890000024
The segmentation output result is 0,D PI The color difference value between one pixel of the image after color space conversion and a reference point pixel is obtained; i is a pixel of the image converted from RGB to Lab color and having three components, I L Representing the first component of the I pixel, I L ＝R Lab ；I a Representing a second component of the I pixel, I a ＝Y Lab ；I b Representing a third component of the I pixel, I b ＝W Lab ；P L Representing the first component of P pixels in the converted image, P a A second component, P, representing P pixels in the converted image b A third component representing a P pixel in the converted image; t is a threshold value for controlling the similarity; will->
Figure FDA0004034327890000025
The other part of the steel billet is divided as a billet body, and the billet conveying tracking is realized by taking the other part as a billet background.
4. The machine vision-based intelligent long billet conveying and tracking method according to claim 1, wherein in the step (5), the cold-fed actual spray-number billet is subjected to identity recognition and confirmation by adopting an image threshold segmentation machine vision algorithm based on a heating stokehole spray code recognition device.
5. A machine vision-based intelligent conveying and tracking system for long billet billets, which adopts the machine vision-based intelligent conveying and tracking method for long billet billets of any one of claims 1 to 4, and comprises a billet discharging control unit (1) and a conveying control unit (2), and is characterized by further comprising:
the system comprises an industrial video machine vision system (3), an intelligent blank discharging subsystem (4), an intelligent conveying subsystem (5), a billboard display system (6) and a robot code spraying system (7);
the industrial video machine vision system (3) is respectively connected with the intelligent blank ejection subsystem (4), the intelligent conveying subsystem (5), the billboard display system (6) and the robot code spraying system (7);
the intelligent ejection subsystem (4) is respectively connected with the ejection control unit (1) and the billboard display system (6);
the intelligent conveying subsystem (5) is respectively connected with the conveying control unit (2) and the billboard display system (6);
the industrial video machine vision system (3) is used for identifying the position, the length and the identity of the steel billet, respectively transmitting the identification result to the intelligent ejection subsystem (4) and the intelligent conveying subsystem (5), and also used for carrying out virtual spraying number with unique identity for each hot-conveyed steel billet;
the intelligent ejection subsystem (4) is used for transmitting baffle lifting and pusher movement control signals of the ejection of the billets to the ejection control unit (1) for execution according to the position, length and identity information of the billets transmitted by the industrial video machine vision system (3);
the intelligent conveying subsystem (5) is used for transmitting signals of starting, stopping and rotating the conveying of the steel billet roller way to the conveying control unit (2) to be executed according to the position, the length and the identity information of the steel billet transmitted by the industrial video machine vision system (3);
the billboard display system (6) is used for displaying the conditions of all-flow billet ejection and conveying identified and operated by the industrial video machine vision system (3), the intelligent ejection subsystem (4) and the intelligent conveying subsystem (5);
the robot code spraying system (7) is used for carrying out unique identity code spraying on off-line steel billets, and when code spraying is carried out, virtual spray codes of the steel billets are obtained from the industrial video machine vision system (3) and code spraying is carried out;
the ejection control unit (1) is used for ejecting steel billets from a casting machine, wherein action execution control command signals of baffle lifting and steel pusher moving come from the intelligent ejection subsystem (4), and an execution result is fed back to the intelligent ejection subsystem (4) after the action execution is finished;
the conveying control unit (2) is used for conveying roller way steel billets, wherein control signals of starting and stopping of roller way conveying and rotation of the rotary table are derived from the intelligent conveying subsystem (5), and an execution result is fed back to the intelligent conveying subsystem (5) after the action is executed.
6. The intelligent long billet conveying and tracking system based on machine vision as claimed in claim 5, wherein the industrial video machine vision system (3) comprises a plurality of industrial cameras, and the installation positions of the industrial cameras comprise a position above a billet cooling bed, a position above a steel moving roller way, a position above a conveying turntable and a position above a conveying roller way.
7. The machine vision-based intelligent long billet conveying and tracking system according to claim 5, wherein the billboard display system (6) adopts a digital twin visualization mode to provide real-time running conditions for production line staff monitoring systems, and displays real-time position conditions of billets recognized by the industrial video machine vision system (3), billet discharging conditions of a casting machine of the intelligent billet discharging subsystem (4), and billet roller conveying conditions of the intelligent conveying subsystem (5).
CN202211276281.4A 2022-10-19 2022-10-19 Intelligent conveying and tracking method and system for small long and square billets based on machine vision Active CN115339879B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211276281.4A CN115339879B (en) 2022-10-19 2022-10-19 Intelligent conveying and tracking method and system for small long and square billets based on machine vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211276281.4A CN115339879B (en) 2022-10-19 2022-10-19 Intelligent conveying and tracking method and system for small long and square billets based on machine vision

Publications (2)

Publication Number Publication Date
CN115339879A CN115339879A (en) 2022-11-15
CN115339879B true CN115339879B (en) 2023-03-31

Family

ID=83957346

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211276281.4A Active CN115339879B (en) 2022-10-19 2022-10-19 Intelligent conveying and tracking method and system for small long and square billets based on machine vision

Country Status (1)

Country Link
CN (1) CN115339879B (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0996634A (en) * 1995-07-27 1997-04-08 Kawasaki Steel Corp Apparatus for testing macro texture of metallic material
CN101716566A (en) * 2009-11-20 2010-06-02 河北钢铁股份有限公司 On-line coating mark spraying machine for continuous cast slabs
CN103175840A (en) * 2011-12-21 2013-06-26 北京兆维电子(集团)有限责任公司 Offset plate surface detection method and system based on machine vision
CN106200448A (en) * 2015-05-09 2016-12-07 精航伟泰测控仪器（北京）有限公司 A kind of industry interface implements long-range mapped system
JP2017218276A (en) * 2016-06-07 2017-12-14 大同特殊鋼株式会社 Transport device
CN108681297A (en) * 2018-04-20 2018-10-19 昆明理工大学 A kind of biological fermentation process control device
CN111633192A (en) * 2020-06-23 2020-09-08 中冶京诚工程技术有限公司 Multi-stream square and round billet ejection system and ejection method
CN113086492A (en) * 2021-05-14 2021-07-09 攀钢集团西昌钢钒有限公司 Casting blank roller way conveying control system and control method

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4523672A (en) * 1981-06-30 1985-06-18 Concast Ag Method for the transverse conveying of strand sections of a multi-strand continuous casting installation and transverse conveying apparatus for a multi-strand casting installation
JP2004307117A (en) * 2003-04-04 2004-11-04 Nippon Steel Corp Device for and method of conveying steel material
CN102324042B (en) * 2011-09-13 2013-11-27 盛乐信息技术（上海）有限公司 Visual recognition system and method
CN105956618B (en) * 2016-04-27 2021-12-03 云南昆钢集团电子信息工程有限公司 Converter steelmaking blowing state identification system and method based on image dynamic and static characteristics
CN105964687B (en) * 2016-06-27 2017-12-08 河北钢铁股份有限公司承德分公司 Track the high-speed wire mill method of single branch strand and monovolume steel product quality state
CN205763056U (en) * 2016-06-27 2016-12-07 河北钢铁股份有限公司承德分公司 For following the tracks of single strand and the automatic number spraying device of monovolume steel product quality state
CN106228545B (en) * 2016-07-14 2018-11-13 西北民族大学 A kind of automatic division method of figure of buddha class Tangka's consistency damaged area
CN114372341A (en) * 2020-10-15 2022-04-19 上海宝信软件股份有限公司 Steel hot rolling pipe control system and method based on digital twinning
CN113102713A (en) * 2021-04-13 2021-07-13 陕西龙门钢铁有限责任公司 Continuous casting and blank discharging method and system based on machine vision
CN114627149A (en) * 2022-01-28 2022-06-14 亚信科技（中国）有限公司 Time-space trajectory simulation method and device, electronic equipment and computer storage medium

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0996634A (en) * 1995-07-27 1997-04-08 Kawasaki Steel Corp Apparatus for testing macro texture of metallic material
CN101716566A (en) * 2009-11-20 2010-06-02 河北钢铁股份有限公司 On-line coating mark spraying machine for continuous cast slabs
CN103175840A (en) * 2011-12-21 2013-06-26 北京兆维电子(集团)有限责任公司 Offset plate surface detection method and system based on machine vision
CN106200448A (en) * 2015-05-09 2016-12-07 精航伟泰测控仪器（北京）有限公司 A kind of industry interface implements long-range mapped system
JP2017218276A (en) * 2016-06-07 2017-12-14 大同特殊鋼株式会社 Transport device
CN108681297A (en) * 2018-04-20 2018-10-19 昆明理工大学 A kind of biological fermentation process control device
CN111633192A (en) * 2020-06-23 2020-09-08 中冶京诚工程技术有限公司 Multi-stream square and round billet ejection system and ejection method
CN113086492A (en) * 2021-05-14 2021-07-09 攀钢集团西昌钢钒有限公司 Casting blank roller way conveying control system and control method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
板坯连铸机出坯系统;仝清秀等;《重型机械》;20090120(第01期);全文 *

Also Published As

Publication number Publication date
CN115339879A (en) 2022-11-15

Similar Documents

Publication Publication Date Title
CN105964687B (en) Track the high-speed wire mill method of single branch strand and monovolume steel product quality state
CN109530456B (en) Continuous casting billet hot feeding and discharging system
CN103878184B (en) Hot rolling rolling line material position remote tracing method
CN112264595B (en) Continuous casting blank fixed-weight cutting control system and control method of multi-flow single scale
CN102581244B (en) Online control system and control method for surface quality of continuous casting billet
CN108549317A (en) Casting blank of continuous casting machine positioning control system and method
CN107321947A (en) A kind of method from motion tracking list branch continuous casting billet quality
CN103143572B (en) Altitude air-cooling coiling tracking and coiling control system
CN108829068A (en) A kind of electroplating assembly line control system and control method
CN112570466B (en) Control method for solving scratch of high-surface thin-specification strip steel conveying roller way
CN115339879B (en) Intelligent conveying and tracking method and system for small long and square billets based on machine vision
CN110667148B (en) Film thickness control system
CN113102713A (en) Continuous casting and blank discharging method and system based on machine vision
CN105241258B (en) Segmented multi-target control system and method for circular cooler
CN106607474A (en) Swing control method for steel plate in front of straightening machine
CN114967627A (en) Casting and rolling integrated material tracking and scheduling method for continuous casting-hot rolling process
CN107695107B (en) A kind of method for tracking and managing of Stand Mill roughing mill setting data
CN205763056U (en) For following the tracks of single strand and the automatic number spraying device of monovolume steel product quality state
CN111368833B (en) Full-automatic steel loading method for detecting slab number based on machine vision
CN202594353U (en) Steel billet detection system for steel billet conveying roller way
CN112267084A (en) System and method for producing zinc-aluminum-magnesium coated steel with high surface quality
CN115435698A (en) System and method for detecting thickness abrasion of high-temperature discharging spiral blade of rotary hearth furnace
CN113649527A (en) 3D prints intelligent sand removal system and 3D and prints production line
CN112247094B (en) Continuous casting blank fixed-weight cutting control system and method
CN201823676U (en) Plane spray line with online reciprocating tracking

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