CN117539210B - Tracking method integrating machine vision and process control - Google Patents
Tracking method integrating machine vision and process control Download PDFInfo
- Publication number
- CN117539210B CN117539210B CN202410029140.5A CN202410029140A CN117539210B CN 117539210 B CN117539210 B CN 117539210B CN 202410029140 A CN202410029140 A CN 202410029140A CN 117539210 B CN117539210 B CN 117539210B
- Authority
- CN
- China
- Prior art keywords
- tracking
- visual monitoring
- materials
- monitoring
- logic
- 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
- 238000000034 method Methods 0.000 title claims abstract description 85
- 238000004886 process control Methods 0.000 title claims abstract description 15
- 239000000463 material Substances 0.000 claims abstract description 146
- 238000012544 monitoring process Methods 0.000 claims abstract description 110
- 230000000007 visual effect Effects 0.000 claims abstract description 70
- 230000008569 process Effects 0.000 claims abstract description 59
- 230000002159 abnormal effect Effects 0.000 claims abstract description 25
- 238000012937 correction Methods 0.000 claims abstract description 21
- 238000004519 manufacturing process Methods 0.000 claims abstract description 17
- 238000005457 optimization Methods 0.000 claims abstract description 17
- 238000011282 treatment Methods 0.000 claims abstract description 6
- 229910000831 Steel Inorganic materials 0.000 claims description 40
- 239000010959 steel Substances 0.000 claims description 40
- 238000012545 processing Methods 0.000 claims description 22
- 238000005520 cutting process Methods 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000005856 abnormality Effects 0.000 claims description 8
- 230000002068 genetic effect Effects 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000004513 sizing Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 238000011369 optimal treatment Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims 2
- 238000006243 chemical reaction Methods 0.000 abstract 1
- 238000005096 rolling process Methods 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 238000001816 cooling Methods 0.000 description 3
- 238000010438 heat treatment Methods 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000014759 maintenance of location Effects 0.000 description 2
- 238000005452 bending Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000005465 channeling Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000009749 continuous casting Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000009628 steelmaking Methods 0.000 description 1
- 230000026676 system process Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/255—Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32252—Scheduling production, machining, job shop
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Automation & Control Theory (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Quality & Reliability (AREA)
- Manufacturing & Machinery (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- General Factory Administration (AREA)
Abstract
The embodiment of the application discloses a tracking method integrating machine vision and process control, which comprises the following steps: the system is provided with a visual monitoring system and a process tracking control system; the visual monitoring system is arranged on the monitoring platform through an industrial camera and is used for collecting video image information; the tracking method further comprises an abnormal tracking automatic correction step, a material one-to-many tracking identity conversion step, a multipath tracking dynamic monitoring optimization step and an automatic judgment error-proofing reminding and optimal disposal step; the visual monitoring system and the process tracking control system are used for automatically correcting the abnormal tracking, converting the material into one-to-many tracking identities, dynamically monitoring and optimizing the multipath tracking, automatically judging, alarming and optimally disposing the process steps, and automatically identifying, judging and disposing all working conditions of the process control, so that the problem of abnormal tracking control treatment of the existing material production can be solved.
Description
Technical Field
The application relates to the technical field of intelligent production control of long steel, in particular to a tracking method integrating machine vision and process control.
Background
The online branch-by-branch tracking is one of key technical functions for realizing the intelligent construction field of long materials, the production process of steel parts is from the beginning of blanks to the end of finished products, the key deformation procedures of rolling, sawing and the like are included in the process of multiple processing deformation, the material pedigree tracking difficulty is high, in order to accurately realize the full-period tracking of each piece of product information, the online production process of the whole steel parts is monitored in real time, different working conditions of each steel part must be strictly tracked, and the steel parts can be accurately tracked only by timely identifying and disposing the processing links and conditions of the steel parts on the production line at the moment.
The complex working conditions faced in the production of long steel materials are as follows:
the multiple sawing lines in the billet area work simultaneously, the single basic automatic logic system is used for unstable number division after multiple lengths are cut, the blanks of the three lines are sent to an outlet roller way by a fixed-length blank through a conveying trolley, and the condition of furnace mixing can occur when multiple furnace numbers are parallel.
And the heating furnace is in an abnormal falling state in the process of clamping and transporting the steel billet by the furnace inlet and outlet clamp.
The steel blocking of the roller way in the rolling area cannot be found at the first time, so that long-time retention is caused.
And bending and tooth channeling of part of steel parts with special steel specifications occur on the cooling bed.
And the steel falls off and the steel piece is askew on the rotary arm at the inlet and outlet of the cooling bed.
The gang saw group is arranged and transported with the steel piece condition of falling behind.
The gang saw is divided into a fixed length and a cut by adopting a single basic automatic logic system, and the division number is unstable.
Multiple gang saw production goes to multiple finishing line complex path transportation condition etc..
Considering the multiple complex working conditions, the single traditional basic automatic logic tracking means is found to have limitation, the problem of the gradual tracking of the long steel production process can be fundamentally solved along with the development and application of the vision AI technology, the problem that the system cannot automatically identify the working conditions and replaces manpower to reduce labor cost is fully solved through practical application, and the intelligent level of the production line is improved.
Accordingly, improvements and developments are still to be made.
Disclosure of Invention
The application provides a tracking method integrating machine vision and process control, which can solve the problem of tracking control processing of the existing material production abnormality.
The application provides a tracking method integrating machine vision and process control, which comprises the following steps:
the system is provided with a visual monitoring system and a process tracking control system;
the visual monitoring system is arranged on the monitoring platform through an industrial camera and is used for collecting video image information;
the tracking method further comprises an abnormal tracking automatic correction step, a material one-to-many tracking step, a multipath tracking dynamic monitoring optimization step and an automatic judging and optimal disposal step;
the visual monitoring system and the process tracking control system are used for the automatic abnormal tracking correction step, the one-to-many tracking step of materials, the dynamic multi-path tracking monitoring optimization step and the automatic judgment error prevention reminding and optimal treatment process step, and are used for completing the automatic identification, judgment and treatment of each working condition of process control.
Optionally, in some embodiments of the application, the method includes:
creating a plurality of logic stations, wherein each logic station is provided with a corresponding label and is installed corresponding to the step;
and setting a tracking algorithm, wherein the tracking algorithm is arranged in the process tracking control system, and the process tracking control system is used for multipoint tracking and correcting control steps.
Optionally, in some embodiments of the present application, the anomaly tracking automatic correction step includes:
acquiring visual identification information from the equipment through a visual monitoring terminal;
Acquiring logic information of basic automatic signal combination, and tracking and estimating position and speed;
And judging the position and speed information of the output steel piece by combining with the type of the logic station, and optimizing the model speed parameter according to the speed and the position.
Optionally, in some embodiments of the present application, the anomaly tracking automatic correction step further includes:
Creating a logic station to distinguish the types of the steps;
the stations are divided into a single tracking station and a plurality of tracking stations.
Optionally, in some embodiments of the present application, the step of tracking the material in one-to-multiple includes a single-piece material cut, the single-piece material cut including:
monitoring the head, tail and sawing position of the material through a visual monitoring system;
calculating the distance between the sawing position and the head and tail and comparing the sawing position with the length of the specified size;
and marking the materials according to the heads and the tails of the materials.
Optionally, in some embodiments of the present application, the step of tracking the material in one-to-multiple manner further includes a plurality of material cuts, the plurality of material cuts including:
monitoring the sequence of the materials through the visual monitoring system;
Marking the position of each material;
monitoring the head, tail and sawing position of the material through a visual monitoring system;
calculating the distance between the sawing position and the head and tail and comparing the sawing position with the length of the specified size;
and marking the materials according to the heads and the tails of the materials.
Optionally, in some embodiments of the present application, the automatically determining and optimizing step includes:
The visual monitoring terminals are arranged at two ends of the equipment;
the visual monitoring terminal acquires a material image to acquire a material count;
and tracking and judging the material counts of the visual monitoring terminals at the two ends, and outputting a judging result.
Optionally, in some embodiments of the present application, the tracking judgment includes:
Acquiring the group count through the visual monitoring terminal;
acquiring information of the visual monitoring terminal through a basic automation system, and performing group arranging and number shifting processing on the information to acquire a logical group arranging count;
comparing the number of the visual monitoring terminal group and the number of the logic group, judging whether the number of the visual monitoring terminal group is consistent with the number of the logic group, and carrying out alarm processing when the number of the logic group is inconsistent with the number of the logic group.
Optionally, in some embodiments of the present application, the step of dynamically monitoring and optimizing the multipath tracking includes calculating the number of material scales and estimating the path idle rate, wherein:
The material sizing quantity calculation comprises the following steps:
calculating the specification of the material;
Calculating the number of the groups according to the specification of the materials;
Cutting by a fixed-length saw according to the number of the rows;
the path idle rate estimation includes:
Identifying a production path through the visual monitoring system;
Information extraction is carried out on the visual monitoring system through a deep convolution network;
calculating the information to generate a two-dimensional relation vector;
And estimating the idle rate of the path according to the two-dimensional relation vector, and judging the running state of the material.
Optionally, in some embodiments of the present application, the multi-path tracking dynamic monitoring optimization step further includes an optimal monitoring path selection, where the optimal monitoring path selection is based on a genetic target algorithm optimal selection model, and the genetic target algorithm optimal selection model calculates and determines the two-dimensional relation vector, and selects according to the estimated idle rate to select an optimal path.
Compared with the prior art, the invention has the beneficial effects that:
1. The invention can track the materials in the whole course by arranging the visual monitoring system and the process tracking control system, record the information of abnormal materials, and the process tracking control system carries out error prompt and correction on the steps to finish the identification, judgment and treatment of the control system.
2. The invention is provided with the tracking algorithm and the logic station, the logic station and the tracking algorithm can be bound, after the abnormal materials are identified, the abnormal information is bound with the label on the logic station, and the tracking algorithm continues tracking and subsequent processing according to the label, so that the processing of the abnormal information is convenient.
3. According to the invention, the materials can be distributed according to the utilization rate of the paths by setting the calculation of the fixed-size quantity of the materials and the calculation of the path idle rate, the processing efficiency of the materials is improved, and the running state of the materials can be judged by setting the two-dimensional relation vector.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a general flow chart of a tracking method for integrating machine vision and process control according to an embodiment of the present application;
FIG. 2 is an overall flowchart of an anomaly tracking automatic correction step provided by an embodiment of the present application;
FIG. 3 is an overall flowchart of the automatic determination and optimization procedure provided in an embodiment of the present application;
fig. 4 is an overall flowchart of tracking determination according to an embodiment of the present application.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, are intended to fall within the scope of the present invention.
Specifically, as shown in fig. 1, the present application provides a tracking method integrating machine vision and process control, comprising the following steps: the system is provided with a visual monitoring system and a process tracking control system; the visual monitoring system is arranged on the monitoring platform system through an industrial camera and is used for collecting video image information; the tracking method further comprises an abnormal tracking automatic correction step, a material one-to-many tracking step, a multipath tracking dynamic monitoring optimization step and an automatic judging and optimal disposal step; the visual monitoring system and the process tracking control system are used for automatically correcting abnormal tracking, tracking materials in one-to-many mode, dynamically monitoring and optimizing multipath tracking, automatically judging error-proofing reminding and optimally disposing process steps, and automatically identifying, judging and processing all working conditions of process control.
In the embodiment of the application, the visual monitoring system and the process tracking control system are both intelligently calculated through AI, the industrial camera is arranged on the monitoring platform system, and the industrial camera is electrically connected with the monitoring platform system, so that the image information acquired by the industrial camera can be transmitted to the monitoring platform system, and the monitoring platform system can conveniently identify the image information, wherein the monitoring platform system processes the image through private or public cloud architecture service, and the specific processing mode is that the image is identified and processed on a server of a cloud architecture through machine identification.
The visual monitoring system and the process tracking control system are used for each process step, so that when each process step is carried out, the visual monitoring system can identify and measure the content of each process step through images, record and digitally process the content of the images, and transmit the content of the images to the process tracking control system, and the process tracking control system can identify the content of the images and control the process flow according to the change of the content of the images, so that the process flow can be carried out according to the normal flow, and errors of the process flow are avoided.
The process mainly comprises the following steps: molten iron pretreatment, converter steelmaking, molten steel refining, continuous casting, finishing cutting and other processes, conveying the steel billet generated in the heating furnace through rollers, positioning and judging materials in the conveying process, and finally entering a cooling bed stage and a gang saw stage to cut the steel.
In the process flow, each link steel can cause problems for processing the steel due to various reasons, for example, in the process of transporting the steel billets by rollers, the steel billets have the corner rolling condition due to incorrect placement angles, or the steel is blocked on a rolling zone roller way to cause long-time retention, and the like, and aiming at various unexpected conditions, corresponding steps are added in each flow, so that each flow can be monitored in real time, the stable operation of the process flow is ensured, and a large amount of manpower and time can be saved.
The method mainly comprises the following four steps: an anomaly tracking automatic correction step, a material one-to-many tracking step, a multipath tracking dynamic monitoring optimization step, an automatic judgment and optimal treatment step, wherein the production of steel is monitored through the four steps, and the anomaly tracking automatic correction step is mainly used for carrying out anomaly judgment and treatment on the position and the speed of a steel piece in a process; the material one-to-many tracking step is mainly used for cutting steel, specifically, the head part, the tail part and the middle part of each steel are precisely cut and marked, and the cut steel is marked; the multipath tracking dynamic monitoring optimizing step is mainly used for distributing steel according to the utilization rate of each assembly line and comparing idle or crowded states of one or more assembly lines; the automatic judging and optimal disposing steps are mainly used for checking and processing the number of the steel materials and avoiding the problem of unmatched number of the steel materials.
Specifically, the method comprises the following steps: creating a plurality of logic stations, wherein each logic station is provided with a corresponding label and is installed in a corresponding step; a tracking algorithm is arranged on a process tracking control system, and the process tracking control system is used for multipoint tracking and correcting control steps.
In the embodiment of the application, the steel on the production line is processed in multiple steps, each step can be processed independently, on the basis, a plurality of logic stations are arranged to mount a visual monitoring system and a process tracking control system on the corresponding logic stations to monitor and process the steps, wherein the logic stations are provided with labels which are in one-to-one correspondence with each flow part and are arranged corresponding to the visual monitoring system and the process tracking control system on the logic stations, and when the stations are abnormal, the visual monitoring system and the process tracking control system on the stations capture the abnormality and bind the abnormality information with the labels to realize the classification of the abnormality information.
When an abnormality occurs on one logic station, the information recorded by the label is stored by the process tracking control system, the process tracking control system can track the abnormality according to the label recorded by the abnormality, the abnormal process can be timely processed through tracking, the specific processing process can be intervened in a manual mode, or the abnormal process can be corrected according to the process tracking control system, and when the abnormal process enables the tracking control system to be unable to automatically correct, the process tracking control system displays the abnormal information through visual data or binds with the personal mobile terminal, so that related personnel can process according to the displayed abnormal information.
Specifically, as shown in fig. 2, the anomaly tracking automatic correction step includes: acquiring visual identification information from the equipment through a visual monitoring terminal; acquiring logic information of basic automatic signal combination, and tracking and estimating position and speed; and judging the position and speed information of the output steel piece by combining with the type of the logic station, and optimizing the model speed parameter according to the speed and the position. The process is mainly carried out in the roller transportation process, and steel billets produced by heating are distributed in the follow-up process after passing through the rollers, wherein for the high efficiency and accuracy of the process, steel on the rollers are required to be marked, the marking content is the speed and the position of the steel, each steel can be marked through the recording of the position, and then each steel can be independently monitored.
The visual monitoring terminal stores a model speed parameter, wherein the model speed parameter is provided with a relational expression of a position S and a speed v:
......
Wherein,
: Correction speed of 1 st sampling time;
: correction speed of 1 st sampling time;
: the correction speed of the t sampling time;
: the material position at the 1 st sampling time;
: material position at sample time 2;
: material position at sample time t.
From the above, it is known that the position of the material is related to the position of the previous material, and the position of the next material can be recorded through the position of the previous material, so that when one of the positions and/or speeds of the materials is abnormal, the speed parameter of the model needs to be optimized, and the influence of the abnormal material on the subsequent material is avoided.
Specifically, the automatic anomaly tracking correction step further includes: creating a logic station to distinguish the types of the steps; the stations are divided into a single tracking station and a plurality of tracking stations. In the embodiment of the application, a single tracking station and a plurality of tracking stations are distinguished according to logic stations, and the specific distinguishing mode is to monitor and judge according to the quantity of materials, wherein when a plurality of circuits exist on the logic stations, the logic stations belong to the plurality of tracking stations, and when only a single circuit exists on the logic stations, the logic stations belong to the single tracking station.
When a single tracking station and a plurality of tracking stations are arranged, the automatic correction step of the anomaly tracking can be used for classifying, processing, tracking and correcting, so that the processing amount of the automatic correction of the anomaly tracking is reduced, and the anomaly processing efficiency is improved.
Specifically, the material one-to-many tracking step includes single material segmentation, and single material segmentation includes: monitoring the head, tail and sawing position of the material through a visual monitoring system; calculating the distance between the sawing position and the head and tail and comparing the sawing position with the length of the specified size; the materials are marked according to the heads and the tails of the materials.
In the embodiment of the application, the single material cutting is mainly used on a single tracking station and is positioned in the finishing cutting process of the material, and when the material is cut, the targeted cutting is carried out according to the specified length of the material, wherein the specified length is the preset length, when the head of the material is cut, the head position of the material can be ensured to be flat, the measurement of the specified length is convenient, and when the material is cut, the tail of the material is cut according to the specified length, so that the material can be accurately cut.
In the process, the materials are required to be arranged and aligned in the cutting process, the positions of the head, the tail and the cutting part of the materials can be provided through the visual monitoring system, the accurate cutting of the materials is convenient, and when the head and tail cutting states are obtained through calculation, the head and tail cutting are abandoned parts and are not numbered; when the states of non-crop and non-crop are obtained through calculation, the visual monitoring system monitors that the part is the material with the fixed length required to be obtained, the material is required to be numbered, namely the number is divided, and the subsequent flow is convenient to conduct targeted treatment on each material.
Specifically, the step of tracking the materials in one part further comprises a plurality of material splitting steps, wherein the plurality of material splitting steps comprise: monitoring the sequence of the materials through a visual monitoring system; marking the position of each material; monitoring the head, tail and sawing position of the material through a visual monitoring system; calculating the distance between the sawing position and the head and tail and comparing the sawing position with the length of the specified size; the materials are marked according to the heads and the tails of the materials.
In the embodiment of the application, the combined cutting of the multiple materials mainly aims at the material processing process of multiple processes, and the basic processing method is the same as that of the cutting of a single material, and the difference is that each material needs to be marked in advance and is marked with a position and a sequence, and when the multiple materials are combined and cut, the cutting is continued according to the marked sequence and the marked position.
Specifically, as shown in fig. 3, the steps of automatically determining and optimizing include: visual monitoring terminals are distributed at two ends of the equipment; the visual monitoring terminal acquires a material image to acquire a material count; and tracking and judging the material counts of the visual monitoring terminals at the two ends, and outputting a judging result. In the embodiment of the application, the process is provided with the visual monitoring terminals which can count the counts of the materials, the situation of the materials can be judged by monitoring the numbers of the materials at the two ends of each working logic station, particularly, the two ends of the whole process flow are provided with the visual monitoring terminals which are mainly used for recording and counting the numbers of the materials and the relative positions of the materials with other materials, the two ends of each logic station are also provided with the visual monitoring terminals which are mainly used for recording the numbers of the materials at the logic station and the relative positions of the materials with other materials, the abnormal points in the materials can be judged by the integral comparison of the numbers of the materials at the whole process flow and each logic station and the relative positions of the materials with other materials, and the positions of the abnormal points can be obtained and output according to the comparison result, so that the abnormal points are convenient for workers and a control system to process and correct.
Specifically, as shown in fig. 4, the tracking judgment includes: acquiring the group count through a visual monitoring terminal; acquiring information of a visual monitoring terminal through a basic automation system, and performing group arranging and number shifting processing on the information to acquire a logical group arranging count; and comparing the number of the visual monitoring terminal groups with the number of the logic groups, judging whether the visual monitoring terminal groups are consistent with the number of the logic groups, and carrying out alarm processing when the visual monitoring terminal groups are inconsistent with the logic groups.
In the embodiment of the application, a tracking judgment process is arranged, and the tracking judgment process is mainly used for comparing the logical group count with the group count of the visual monitoring terminal, wherein the logical group count is the count of a material of a logical group, when the material is logically arranged, the count is obtained, and compared with the group count in the visual monitoring terminal, when the comparison is inconsistent, the alarm output is carried out, the abnormal processing is convenient for staff, and when the comparison is inconsistent, the alarm output is not carried out.
Specifically, the multipath tracking dynamic monitoring optimization step comprises the steps of calculating the number of the fixed sizes of materials and estimating the path idle rate, wherein: the material sizing quantity calculation includes: calculating the specification of the material; calculating the number of the groups according to the specification of the materials; cutting by a fixed-length saw according to the number of the rows; the path idle rate estimation includes: identifying a production path through a visual monitoring system; information extraction is carried out on the visual monitoring system through a deep convolution network; calculating the information to generate a two-dimensional relation vector; and estimating the idle rate of the path according to the two-dimensional relation vector, and judging the running state of the material.
According to the embodiment of the application, the calculation of the set material fixed-length number can determine the number of the groups of materials according to the specifications of different sizes, fixed-length cutting is performed according to the different numbers of the groups, and path selection of the materials is conveniently performed by multipath tracking dynamic monitoring optimization, wherein the path selection is mainly performed by calculating each production path for dynamic identification, a two-dimensional relation vector is made according to the relation between the quantity of the materials and time, idle paths are conveniently deduced according to the two-dimensional relation vector by multipath tracking dynamic monitoring optimization, and the materials are conveniently distributed.
Specifically, the multipath tracking dynamic monitoring optimization step further comprises optimal monitoring path selection, wherein the optimal monitoring path selection is based on a genetic target algorithm optimal selection model, the genetic target algorithm optimal selection model calculates and judges the two-dimensional relation vector, and the optimal path is selected according to the estimated idle rate.
In the embodiment of the application, an objective algorithm is arranged to perform algorithm optimization on the two-dimensional relation vector, wherein the objective algorithm is based on a multi-objective optimization selection model of a genetic algorithm, an objective function ,/>,/> is used, n is the number of targets, is the objective function under a certain single target, and a constraint is defined by/, so that the optimal path is obtained.
In the description and claims of the present application, the words "comprise/comprising" and the words "have/include" and variations thereof are used to specify the presence of stated features, values, steps, or components, but do not preclude the presence or addition of one or more other features, values, steps, components, or groups thereof.
Some features of the application, which are, for clarity of illustration, described in the context of separate embodiments, may also be provided in combination in a single embodiment. Conversely, some features of the application, which are, for brevity, described in the context of a single embodiment, may also be provided separately or in any suitable combination in different embodiments.
The foregoing description of the preferred embodiment of the application is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the application.
Claims (3)
1. The tracking method integrating the machine vision and the process control is characterized by comprising an abnormal tracking automatic correction step, a material one-to-many tracking step, a multipath tracking dynamic monitoring optimization step and an automatic judging and optimal disposal step;
wherein, the automatic correction step of anomaly tracking includes:
acquiring visual identification information from the equipment through a visual monitoring terminal;
Acquiring logic information of basic automatic signal combination, and tracking and estimating position and speed;
Judging the position and speed information of the output steel piece by combining with the type of the logic station, and optimizing model speed parameters according to the speed and the position;
The material one-to-many tracking step comprises single material cutting and multiple material cutting, wherein the single material cutting and the multiple material cutting are respectively performed according to the specified length when the materials are cut;
the single material segmentation includes:
monitoring the head, tail and sawing position of the material through a visual monitoring system;
calculating the distance between the sawing position and the head and tail and comparing the sawing position with the length of the specified size;
Dividing the materials according to the head and tail of the materials;
The multi-branch material segmentation comprises:
monitoring the sequence of the materials through the visual monitoring system;
Marking the position of each material;
monitoring the head, tail and sawing position of the material through a visual monitoring system;
calculating the distance between the sawing position and the head and tail and comparing the sawing position with the length of the specified size;
Dividing the materials according to the head and tail of the materials;
the multipath tracking dynamic monitoring optimization step comprises the steps of selecting paths of the materials, calculating each production path for dynamic identification, and distributing the materials;
The multipath tracking dynamic monitoring optimization step comprises the steps of material sizing quantity calculation, path idle rate estimation and optimal monitoring path selection, wherein:
The material sizing quantity calculation comprises the following steps:
calculating the specification of the material;
Calculating the number of the groups according to the specification of the materials;
Cutting by a fixed-length saw according to the number of the rows;
the path idle rate estimation includes:
Identifying a production path through the visual monitoring system;
Information extraction is carried out on the visual monitoring system through a deep convolution network;
calculating the information to generate a two-dimensional relation vector;
estimating the idle rate of the path according to the two-dimensional relation vector, and judging the running state of the material;
The optimal monitoring path selection is based on a genetic target algorithm optimal selection model, the genetic target algorithm optimal selection model calculates and judges the two-dimensional relation vector, and the optimal monitoring path selection is performed according to the estimated idle rate so as to select an optimal path;
The automatic judging and optimal disposing steps comprise:
The visual monitoring terminals are arranged at two ends of the equipment;
the visual monitoring terminal acquires a material image to acquire a material count;
tracking and judging the material counts of the visual monitoring terminals at the two ends, and outputting a judging result;
wherein the tracking judgment includes:
Acquiring the group count through the visual monitoring terminal;
acquiring information of the visual monitoring terminal through a basic automation system, and performing group arranging and number shifting processing on the information to acquire a logical group arranging count;
comparing the number of the visual monitoring terminal group and the number of the logic group, judging whether the number of the logic group is consistent, and carrying out alarm processing when the number of the logic group is inconsistent;
the tracking method further comprises the following steps:
the system is provided with a visual monitoring system and a process tracking control system;
the visual monitoring system is arranged on the monitoring platform through an industrial camera and is used for collecting video image information;
The visual monitoring system and the process tracking control system are used for the automatic abnormality tracking correction step, the one-to-many tracking step of materials, the dynamic multi-path tracking monitoring optimization step and the automatic judgment and optimal treatment step, and are used for completing the automatic identification, judgment and treatment of each working condition of process control.
2. The method of tracking a fusion of machine vision and process control of claim 1, comprising:
creating a plurality of logic stations, wherein each logic station is provided with a corresponding label and is installed corresponding to the step;
and setting a tracking algorithm, wherein the tracking algorithm is arranged in the process tracking control system, and the process tracking control system is used for multipoint tracking and correcting control steps.
3. The method of tracking a fusion of machine vision and process control of claim 1, wherein the anomaly tracking automatic correction step further comprises:
Creating a logic station to distinguish the types of the steps;
the stations are divided into a single tracking station and a plurality of tracking stations.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410029140.5A CN117539210B (en) | 2024-01-09 | 2024-01-09 | Tracking method integrating machine vision and process control |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410029140.5A CN117539210B (en) | 2024-01-09 | 2024-01-09 | Tracking method integrating machine vision and process control |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117539210A CN117539210A (en) | 2024-02-09 |
CN117539210B true CN117539210B (en) | 2024-04-16 |
Family
ID=89786550
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410029140.5A Active CN117539210B (en) | 2024-01-09 | 2024-01-09 | Tracking method integrating machine vision and process control |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117539210B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101751021A (en) * | 2008-12-19 | 2010-06-23 | 鞍钢集团工程技术有限公司 | Seamless steel tube production process information tracking method |
CN114037752A (en) * | 2021-10-25 | 2022-02-11 | 北京科技大学设计研究院有限公司 | Cold bed area steel plate tracking method based on multi-model information matching |
CN114425561A (en) * | 2021-12-15 | 2022-05-03 | 承德建龙特殊钢有限公司 | Seamless steel pipe tracking production system one by one |
CN114472527A (en) * | 2021-12-15 | 2022-05-13 | 承德建龙特殊钢有限公司 | Seamless steel pipe tracking production system one by one |
CN117002947A (en) * | 2023-07-21 | 2023-11-07 | 北京科技大学设计研究院有限公司 | Visual detection-based automatic tracking method and system for steel rail diversion |
WO2024001632A1 (en) * | 2022-06-29 | 2024-01-04 | 中冶华天工程技术有限公司 | Casting and rolling integrated material tracking and scheduling method for continuous casting-hot rolling process |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11526834B2 (en) * | 2017-08-03 | 2022-12-13 | Overhaul Group, Inc. | Tracking system and method for monitoring and ensuring security of shipments |
-
2024
- 2024-01-09 CN CN202410029140.5A patent/CN117539210B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101751021A (en) * | 2008-12-19 | 2010-06-23 | 鞍钢集团工程技术有限公司 | Seamless steel tube production process information tracking method |
CN114037752A (en) * | 2021-10-25 | 2022-02-11 | 北京科技大学设计研究院有限公司 | Cold bed area steel plate tracking method based on multi-model information matching |
CN114425561A (en) * | 2021-12-15 | 2022-05-03 | 承德建龙特殊钢有限公司 | Seamless steel pipe tracking production system one by one |
CN114472527A (en) * | 2021-12-15 | 2022-05-13 | 承德建龙特殊钢有限公司 | Seamless steel pipe tracking production system one by one |
WO2024001632A1 (en) * | 2022-06-29 | 2024-01-04 | 中冶华天工程技术有限公司 | Casting and rolling integrated material tracking and scheduling method for continuous casting-hot rolling process |
CN117002947A (en) * | 2023-07-21 | 2023-11-07 | 北京科技大学设计研究院有限公司 | Visual detection-based automatic tracking method and system for steel rail diversion |
Also Published As
Publication number | Publication date |
---|---|
CN117539210A (en) | 2024-02-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108537301A (en) | A kind of accurate retroactive method of full process of aluminium alloy compression casting product | |
CN109877158B (en) | CSP continuous casting and rolling temporary steel coil number automatic matching method and system | |
CN114473249B (en) | Pole piece die cutting method and system | |
CN117539210B (en) | Tracking method integrating machine vision and process control | |
CN110756749A (en) | Billet length measuring method | |
CN109894481A (en) | Continuous rolling production line cold bed material tracking method, apparatus, system and medium | |
CN110802305B (en) | Online monitoring device and monitoring method for arc welding process parameters | |
CN117196416B (en) | Equipment state monitoring system driven by industrial middle platform | |
CN110044183B (en) | Fang detection automatic feeding method based on machine vision | |
CN103870949B (en) | A kind of metallurgical production Process Tracking system and method | |
CN114749497A (en) | Intelligent profile steel finishing production line | |
CN115301747B (en) | Cooling bed area material tracking system and method based on multi-target identification and tracking | |
CN113240244A (en) | Automatic casting blank grading judgment method suitable for tracking steel-making production | |
CN108941496B (en) | Real-time tracking and controlling system and method for quality of steelmaking continuous casting process | |
CN112224788B (en) | Control method for automatically positioning intelligent logistics conveying line | |
CN115318845B (en) | Method and system for tracking branch-by-branch material of whole process of hot-rolled seamless steel tube | |
CN103512887A (en) | Method for bundling surface quality information of band steel | |
CN110187676A (en) | A kind of pallet fork workshop digital management system | |
CN109590341A (en) | A kind of cold rolling continuous processing line strip location tracking method | |
CN115415319A (en) | End-to-end whole process tracing method for multi-machine multi-flow casting blank production | |
CN112650789A (en) | Monitoring and early warning system of steel product data channel | |
CN117812594B (en) | Internet of things network security system and control method thereof | |
CN118095804B (en) | Renewable resource traceability management method and system | |
CN111846315B (en) | System and method for acquiring and analyzing production loss time of filling production line equipment | |
CN115810010B (en) | Train pantograph online 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 |