CN116277001A - Continuous casting robot management method and system based on digital twin - Google Patents
Continuous casting robot management method and system based on digital twin Download PDFInfo
- Publication number
- CN116277001A CN116277001A CN202310285814.3A CN202310285814A CN116277001A CN 116277001 A CN116277001 A CN 116277001A CN 202310285814 A CN202310285814 A CN 202310285814A CN 116277001 A CN116277001 A CN 116277001A
- Authority
- CN
- China
- Prior art keywords
- continuous casting
- casting robot
- model
- robot
- dimensional
- 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.)
- Pending
Links
- 238000009749 continuous casting Methods 0.000 title claims abstract description 607
- 238000007726 management method Methods 0.000 title claims abstract description 101
- 230000000007 visual effect Effects 0.000 claims abstract description 128
- 230000003068 static effect Effects 0.000 claims abstract description 107
- 238000001514 detection method Methods 0.000 claims abstract description 103
- 238000010276 construction Methods 0.000 claims abstract description 62
- 238000000034 method Methods 0.000 claims abstract description 30
- 238000003745 diagnosis Methods 0.000 claims description 77
- 238000009877 rendering Methods 0.000 claims description 21
- 238000013461 design Methods 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 16
- 238000013500 data storage Methods 0.000 claims description 12
- 238000010801 machine learning Methods 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 description 6
- 229910000831 Steel Inorganic materials 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 4
- 239000010959 steel Substances 0.000 description 4
- 238000011835 investigation Methods 0.000 description 3
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 239000001301 oxygen Substances 0.000 description 2
- 229910052760 oxygen Inorganic materials 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009529 body temperature measurement Methods 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000001257 hydrogen Substances 0.000 description 1
- 229910052739 hydrogen Inorganic materials 0.000 description 1
- 125000004435 hydrogen atom Chemical class [H]* 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000002893 slag Substances 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1628—Programme controls characterised by the control loop
- B25J9/163—Programme controls characterised by the control loop learning, adaptive, model based, rule based expert control
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
-
- 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]
Abstract
The invention belongs to the technical field of continuous casting robots, and discloses a continuous casting robot management method and system based on digital twinning. The method comprises the following steps: constructing a continuous casting digital factory three-dimensional static model; constructing a continuous casting digital factory three-dimensional dynamic model provided with a visual interface; constructing a continuous casting digital factory three-dimensional dynamic model provided with a continuous casting robot operation detection database; and managing the continuous casting robot by using a continuous casting digital factory three-dimensional dynamic model provided with a continuous casting robot operation detection database according to the real-time equipment operation data and the real-time operation work data. The system comprises a model construction unit, a database construction unit and a management application unit. The invention solves the problems of large labor cost investment, safety risk, low intelligent degree, poor management convenience, poor user experience and low system practicability in the prior art.
Description
Technical Field
The invention belongs to the technical field of continuous casting robots, and particularly relates to a continuous casting robot management method and system based on digital twinning.
Background
In the work area of continuous casting machine system, continuous casting robot installs in the middle package region mostly for carry out the molten steel temperature measurement in the big package, decide hydrogen, sample, middle package adds covering agent, ladle long mouth of a river loading and unloading, long mouth of a river oxygen clearance and non-automatic when starting water burn oxygen drainage blow open ladle mouth of a river etc. operation work, avoided adopting the staff that the manual mode exists to expose in high temperature and dust environment healthy, the problem that operation work intensity is big to and middle package or the inside reaction splash of ladle, the dangerous problem that crust slag dropped from the ladle, guarantee continuous stable and the quality of product of continuous casting technology.
However, the existing continuous casting robot has problems or anomalies in any link in the production process, the action of the continuous casting robot can be stopped at the stage, the automation degree is low, the on-site analysis is needed to be carried out by manpower, the fault or anomaly reasons are checked, the work of the continuous casting robot is restarted according to the specific conditions, the labor cost is high, and the safety risk is also caused during the on-site analysis; the existing continuous casting robot management or monitoring system can only receive alarm signals sent by the continuous casting robot, and cannot know specific conditions of faults or anomalies, so that the intelligent degree is low, and the management convenience is poor; and critical part data or equipment diagnosis work requires observation and investigation after the continuous casting machine or the continuous casting robot stops operating, which often takes a lot of time and cost; finally, the data transmitted back by the continuous casting robot are often based on a format which can be understood by a computer program, a worker needs to understand the working condition and the action state of the current continuous casting robot after professional translation and decoding, the user experience is poor, and the system practicability is low.
Disclosure of Invention
The invention aims to solve the problems of large labor cost investment, safety risk, low intelligent degree, poor management convenience, poor user experience and low system practicability in the prior art, and provides a continuous casting robot management method and system based on digital twinning.
The technical scheme adopted by the invention is as follows:
a continuous casting robot management method based on digital twinning comprises the following steps:
constructing a continuous casting digital factory three-dimensional static model;
constructing a continuous casting robot three-dimensional dynamic model in a continuous casting digital factory three-dimensional static model, and performing visual design on the continuous casting robot three-dimensional dynamic model to obtain the continuous casting digital factory three-dimensional dynamic model provided with a visual interface;
constructing a continuous casting robot operation detection database, and adding the continuous casting robot operation detection database to the continuous casting digital factory three-dimensional dynamic model provided with the visual interface to obtain the continuous casting digital factory three-dimensional dynamic model provided with the continuous casting robot operation detection database;
and acquiring equipment operation data and operation work data of the continuous casting robot in real time, and managing the continuous casting robot by using a continuous casting digital factory three-dimensional dynamic model provided with a continuous casting robot operation detection database according to the real-time equipment operation data and the real-time operation work data.
Further, constructing a continuous casting digital factory three-dimensional static model, which comprises the following steps:
constructing an initial continuous casting digital factory three-dimensional static model according to a process building drawing of a continuous casting factory;
correcting the initial continuous casting digital factory three-dimensional static model according to the site three-dimensional scanning video of the continuous casting reality factory to obtain a final continuous casting digital factory three-dimensional static model;
correcting the initial continuous casting digital factory three-dimensional static model according to the on-site three-dimensional scanning video of the continuous casting real factory to obtain the final continuous casting digital factory three-dimensional static model, comprising the following steps:
performing frame interception on the site three-dimensional scanning video of the continuous casting reality factory to obtain site three-dimensional scanning images of continuous frames;
acquiring view angle coordinates of a factory site view angle according to site three-dimensional scanning images of a plurality of frames which are random and discontinuous;
aligning the view angle coordinates of the factory site view angle with the view angle coordinates of the preset view angle of the initial continuous casting digital factory three-dimensional static model for one time to obtain the view angle coordinates of the preset view angle after one time alignment;
and correcting the initial continuous casting digital factory three-dimensional static model according to the on-site three-dimensional scanning image of the continuous frame based on the once aligned visual angle coordinates of the preset visual angle to obtain the final continuous casting digital factory three-dimensional static model.
Further, in the continuous casting digital factory three-dimensional static model, constructing a continuous casting robot three-dimensional dynamic model, and carrying out visual design on the continuous casting robot three-dimensional dynamic model to obtain the continuous casting digital factory three-dimensional dynamic model provided with a visual interface, comprising the following steps:
constructing an initial continuous casting robot three-dimensional static model according to the equipment drawing of the continuous casting robot;
according to the position data of the continuous casting robot in the process drawing of the continuous casting plant, adding the initial continuous casting robot three-dimensional static model to the corresponding position of the continuous casting digital plant three-dimensional static model;
correcting and dynamically converting the initial continuous casting robot three-dimensional static model according to the equipment three-dimensional scanning video of the continuous casting robot and the action three-dimensional scanning video corresponding to each action gesture to obtain a continuous casting robot three-dimensional dynamic model for dynamically displaying the action gesture of the continuous casting robot;
and adding a visual management interface into the three-dimensional dynamic model of the continuous casting robot, and establishing a display link between the visual management interface and equipment operation data and operation work data of the continuous casting robot to obtain the three-dimensional dynamic model of the continuous casting digital factory provided with the visual interface.
Further, according to the equipment three-dimensional scanning video of the continuous casting robot, the action three-dimensional scanning video corresponding to each action gesture and historical equipment operation data, correcting and dynamically converting the initial continuous casting robot three-dimensional static model to obtain a continuous casting robot three-dimensional dynamic model for dynamically displaying the action gesture of the continuous casting robot, comprising the following steps:
performing frame interception on the equipment three-dimensional scanning video of the continuous casting robot to obtain equipment three-dimensional scanning images of continuous frames;
acquiring view angle coordinates of a field view angle of the equipment according to equipment three-dimensional scanning images of a plurality of frames which are random and discontinuous;
performing secondary alignment on the view angle coordinates of the field view angle of the equipment and the view angle coordinates of the preset view angle after primary alignment of the three-dimensional static model of the continuous casting digital factory to obtain the view angle coordinates of the preset view angle after secondary alignment;
correcting the initial continuous casting robot three-dimensional static model based on the view angle coordinates of the preset view angles after secondary alignment according to the equipment three-dimensional scanning images of the continuous frames to obtain a final continuous casting robot three-dimensional static model;
the method comprises the steps of respectively carrying out frame interception on an action three-dimensional scanning video corresponding to each action gesture of the continuous casting robot to obtain an action three-dimensional scanning image of a continuous frame corresponding to each action gesture;
And based on the view angle coordinates of the preset view angle after the secondary alignment, respectively carrying out dynamic conversion on the final continuous casting robot three-dimensional static model according to the motion three-dimensional scanning images of the continuous frames corresponding to each motion gesture, and obtaining the continuous casting robot three-dimensional dynamic model for dynamically displaying the motion gesture of the continuous casting robot.
Further, a continuous casting robot operation detection database is constructed, and the continuous casting robot operation detection database is added to a continuous casting digital factory three-dimensional dynamic model provided with a visual interface, so that the continuous casting digital factory three-dimensional dynamic model provided with the continuous casting robot operation detection database is obtained, and the method comprises the following steps:
establishing a corresponding relation between historical equipment operation data of the continuous casting robot and operation types, adding the corresponding operation types as type labels to the corresponding historical equipment operation data to obtain a plurality of historical equipment operation data provided with the type labels;
establishing a corresponding relation between historical operation work data of each operation work type and a preset operation work threshold;
training by using a machine learning algorithm according to a plurality of historical equipment operation data provided with type labels, and constructing a continuous casting robot operation work recognition model;
Training by using a machine learning algorithm according to a plurality of historical equipment operation data provided with fault labels, and constructing a continuous casting robot fault diagnosis model;
collecting historical equipment operation data, historical operation work data, model metadata of a continuous casting robot operation work identification model and model metadata of a continuous casting robot fault diagnosis model, constructing a continuous casting robot operation detection database, and adding the continuous casting robot operation detection database to a continuous casting digital factory three-dimensional dynamic model provided with a visual interface;
and establishing a visual management interface of the continuous casting digital plant three-dimensional dynamic model and a display link of the continuous casting robot fault diagnosis model, and a visual management interface of the continuous casting digital plant three-dimensional dynamic model and a display link of the continuous casting robot fault diagnosis model to obtain the continuous casting digital plant three-dimensional dynamic model provided with the continuous casting robot operation detection database.
Further, equipment operation data and operation work data of the continuous casting robot are collected in real time, and according to the real-time equipment operation data and the real-time operation work data, a continuous casting digital factory three-dimensional dynamic model provided with a continuous casting robot operation detection database is used for managing the continuous casting robot, and the method comprises the following steps:
Collecting equipment operation data and operation work data of the continuous casting robot in real time, and storing the real-time equipment operation data and the real-time operation work data into an operation detection database of the continuous casting robot;
calling a continuous casting robot fault diagnosis model in a continuous casting robot operation detection database to carry out fault diagnosis according to real-time equipment operation data, obtaining a fault diagnosis result of the continuous casting robot, and displaying the real-time equipment operation data and the fault diagnosis result on a visual management interface;
according to the real-time operation data, calling a continuous casting robot operation recognition model in a continuous casting robot operation detection database to perform operation recognition to obtain an operation type of the continuous casting robot, and displaying the real-time operation data and the operation type on a visual management interface;
according to the real-time operation work data and the operation work types thereof, matching the historical operation work data of the corresponding operation work types, according to the corresponding relation between the historical operation work data of the operation work types and the preset operation work threshold, comparing the real-time operation work data with the preset operation work threshold in a numerical mode to obtain the operation work condition of the continuous casting robot, and displaying the operation work condition on a visual management interface.
The continuous casting robot management system based on the digital twin is used for realizing a continuous casting robot management method, and comprises a model building unit, a database building unit and a management application unit, wherein the model building unit, the database building unit and the management application unit are sequentially connected, and the management application unit, the database building unit and the model building unit are all connected with an external factory data server;
the model construction unit is used for extracting a building drawing and an on-site three-dimensional scanning video of the continuous casting reality factory, which are stored by the factory data server, and an equipment drawing, an equipment three-dimensional scanning video and an action three-dimensional scanning video of the continuous casting robot, constructing a continuous casting digital factory three-dimensional static model according to a process drawing and an on-site three-dimensional scanning video of the continuous casting factory, constructing a continuous casting robot three-dimensional dynamic model in the continuous casting digital factory three-dimensional static model according to the equipment drawing, the equipment three-dimensional scanning video and the action three-dimensional scanning video of the continuous casting robot, and carrying out visual design on the continuous casting robot three-dimensional dynamic model to obtain the continuous casting digital factory three-dimensional dynamic model provided with a visual interface;
the database construction unit is used for extracting historical equipment operation data and historical operation work data of the continuous casting robot stored by the factory data server, constructing a continuous casting robot operation detection database according to the historical equipment operation data and the historical operation work data of the continuous casting robot, and adding the continuous casting robot operation detection database to the continuous casting digital factory three-dimensional dynamic model provided with the visual interface to obtain the continuous casting digital factory three-dimensional dynamic model provided with the continuous casting robot operation detection database;
The management application unit is used for rendering the continuous casting digital factory three-dimensional dynamic model provided with the continuous casting robot operation detection database, extracting real-time equipment operation data and real-time operation work data stored by the factory data server, and managing the continuous casting robot by using the continuous casting digital factory three-dimensional dynamic model provided with the continuous casting robot operation detection database according to the real-time equipment operation data and the real-time operation work data.
Further, the model building unit comprises a static model building module, a dynamic model building module and a visual design module, wherein the static model building module, the dynamic model building module and the visual design module are sequentially connected, the static model building module and the dynamic model building module are connected with an external factory data server, and the visual design module is connected with the database building unit;
the static model construction module is used for extracting a building drawing and a field three-dimensional scanning video of the continuous casting reality factory stored by the factory data server, constructing an initial continuous casting digital factory three-dimensional static model according to a process drawing of the continuous casting factory, correcting the initial continuous casting digital factory three-dimensional static model according to the field three-dimensional scanning video of the continuous casting reality factory to obtain a final continuous casting digital factory three-dimensional static model, extracting an equipment drawing, an equipment three-dimensional scanning video and an action three-dimensional scanning video of the continuous casting robot stored by the factory data server, constructing an initial continuous casting robot three-dimensional static model according to the equipment drawing of the continuous casting robot, and adding the initial continuous casting robot three-dimensional static model to a corresponding position of the continuous casting digital factory three-dimensional static model according to position data of the continuous casting robot in the process drawing of the continuous casting factory;
The dynamic model construction module is used for correcting and dynamically converting the initial continuous casting robot three-dimensional static model according to the equipment three-dimensional scanning video of the continuous casting robot and the action three-dimensional scanning video corresponding to each action gesture to obtain a continuous casting robot three-dimensional dynamic model for dynamically displaying the action gesture of the continuous casting robot;
the visual design module is used for adding a visual management interface to the continuous casting robot three-dimensional dynamic model, establishing a display link between the visual management interface and equipment operation data and operation work data of the continuous casting robot, obtaining a continuous casting digital factory three-dimensional dynamic model provided with the visual interface, and sending the continuous casting digital factory three-dimensional dynamic model provided with the visual interface to the database construction unit.
Further, the database construction unit comprises a corresponding relation establishment module, a continuous casting robot operation work identification model construction module, a continuous casting robot fault diagnosis model construction module, a continuous casting robot operation detection database construction module and a visual linkage module, wherein the corresponding relation establishment module, the continuous casting robot operation work identification model construction module, the continuous casting robot fault diagnosis model construction module, the continuous casting robot operation detection database construction module and the visual linkage module are sequentially connected, and the corresponding relation establishment module is respectively connected with the model construction unit and an external factory data server, and the visual linkage module is connected with the management application unit;
The corresponding relation establishing module is used for receiving the continuous casting digital factory three-dimensional dynamic model provided with the visual interface and sent by the model constructing unit, extracting the historical equipment operation data of the continuous casting robot and the historical operation work data stored by the factory data server, establishing the corresponding relation between the historical equipment operation data of the continuous casting robot and the operation work types, taking the corresponding operation work types as type labels, adding the type labels to the corresponding historical equipment operation data to obtain a plurality of historical equipment operation data provided with the type labels, and establishing the corresponding relation between the historical operation work data of each operation work type and a preset operation work threshold;
the continuous casting robot operation work recognition model construction module is used for training by using a machine learning algorithm according to a plurality of historical equipment operation data provided with type labels to construct a continuous casting robot operation work recognition model;
the continuous casting robot fault diagnosis model construction module is used for training by using a machine learning algorithm according to a plurality of historical equipment operation data provided with fault labels to construct a continuous casting robot fault diagnosis model;
the continuous casting robot operation detection database construction module is used for collecting historical equipment operation data, historical operation work data, model metadata of a continuous casting robot operation work identification model and model metadata of a continuous casting robot fault diagnosis model, constructing a continuous casting robot operation detection database, and adding the continuous casting robot operation detection database to a continuous casting digital factory three-dimensional dynamic model provided with a visual interface;
The visual linkage module is used for establishing a visual management interface of the continuous casting digital plant three-dimensional dynamic model and a display link of the continuous casting robot fault diagnosis model and a visual management interface of the continuous casting digital plant three-dimensional dynamic model and a display link of the continuous casting robot fault diagnosis model, obtaining the continuous casting digital plant three-dimensional dynamic model provided with the continuous casting robot operation detection database, and sending model metadata of the continuous casting digital plant three-dimensional dynamic model provided with the continuous casting robot operation detection database to the management application unit.
Further, the management application unit comprises a model rendering module, a real-time data storage module, a fault diagnosis module, an operation work identification module and an operation work condition judging module, wherein the model rendering module, the real-time data storage module, the fault diagnosis module, the operation work identification module and the operation work condition judging module are sequentially connected, the model rendering module is connected with the database construction unit, and the real-time data storage module is connected with an external factory data server;
the model rendering module is used for rendering according to the model metadata of the continuous casting digital factory three-dimensional dynamic model provided with the continuous casting robot operation detection database and sent by the database construction unit, so as to obtain a rendered continuous casting digital factory three-dimensional dynamic model provided with the continuous casting robot operation detection database;
A real-time data storage module for extracting real-time equipment operation data and real-time operation work data stored in the factory data server,
the continuous casting digital factory three-dimensional dynamic model is constructed by the rendering model construction unit and the database construction unit and is provided with a continuous casting robot operation detection database, real-time equipment operation data and real-time operation work data stored by a factory data server are extracted, and the real-time equipment operation data and the real-time operation work data are stored in the continuous casting robot operation detection database;
the fault diagnosis module is used for establishing a continuous casting robot fault diagnosis model according to model metadata of the continuous casting robot fault diagnosis model in the continuous casting robot operation detection database, calling the continuous casting robot fault diagnosis model in the continuous casting robot operation detection database to carry out fault diagnosis according to real-time equipment operation data to obtain a fault diagnosis result of the continuous casting robot, and displaying the real-time equipment operation data and the fault diagnosis result on the visual management interface;
the operation work identification module is used for establishing a continuous casting robot operation work identification model according to model metadata of the continuous casting robot operation work identification model in the continuous casting robot operation detection database, calling the continuous casting robot operation work identification model in the continuous casting robot operation detection database to conduct operation work identification according to real-time operation work data to obtain an operation work type of the continuous casting robot, and displaying the real-time operation work data and the operation work type on the visual management interface;
The operation working condition judging module is used for matching the historical operation working data of the corresponding operation working type according to the real-time operation working data and the operation working type thereof, comparing the real-time operation working data with a preset operation working threshold value according to the corresponding relation between the historical operation working data of the operation working type and the preset operation working threshold value to obtain the operation working condition of the continuous casting robot, and displaying the operation working condition on the visual management interface.
The beneficial effects of the invention are as follows:
according to the continuous casting robot management method and system based on digital twin, the overall situation of a continuous casting reality factory is simulated based on the three-dimensional static model of the continuous casting digital factory, the user immersive experience degree is improved, the continuous casting robot is visually managed through the three-dimensional dynamic model of the continuous casting robot, the situation that the continuous casting robot is manually analyzed on site is avoided, the labor cost investment is reduced, the safety is improved, the continuous casting robot operation detection database is built and used for storing historical or real-time equipment operation data and operation work data, data support is provided for continuous casting robot operation situation analysis, the accuracy of the model and the data is improved, the observation and investigation of the continuous casting robot are avoided, the operation work recognition and fault diagnosis functions are provided, the intelligent degree and convenience of management are improved, the operation situation and the operation state of the continuous casting robot can be visually and conveniently observed through the visual interface, and the specific situation of data expression is intuitively understood, and the user experience and the system practicability are improved.
Other advantageous effects of the present invention will be further described in the detailed description.
Drawings
Fig. 1 is a block flow diagram of a continuous casting robot management method based on digital twinning in the present invention.
Fig. 2 is a block diagram of a digital twin-based continuous casting robot management system according to the present invention.
Description of the embodiments
The invention is further illustrated by the following description of specific embodiments in conjunction with the accompanying drawings.
Examples
As shown in fig. 1, the present embodiment provides a continuous casting robot management method based on digital twinning, which includes the following steps:
the method for constructing the continuous casting digital factory three-dimensional static model comprises the following steps:
constructing an initial continuous casting digital factory three-dimensional static model according to a process drawing of a continuous casting factory; the continuous casting robot management is arranged in the digital world based on the digital twin technology, so that management or detection tasks in an actual scene are avoided, safety accidents are avoided, and the safety of staff is improved;
correcting the initial continuous casting digital factory three-dimensional static model according to the on-site three-dimensional scanning video of the continuous casting real factory to obtain the final continuous casting digital factory three-dimensional static model, comprising the following steps:
performing frame interception on the site three-dimensional scanning video of the continuous casting reality factory to obtain site three-dimensional scanning images of continuous frames;
Acquiring view angle coordinates of a factory site view angle according to site three-dimensional scanning images of a plurality of frames which are random and discontinuous;
the visual angle coordinates of the field visual angle of the factory are aligned with the visual angle coordinates of the preset visual angle of the initial continuous casting digital factory three-dimensional static model for one time, so that the visual angle coordinates of the preset visual angle after one time alignment are obtained, the visual angles of the digital world and the physical world are unified, and the user experience of the continuous casting digital factory three-dimensional static model is improved;
correcting the initial continuous casting digital factory three-dimensional static model based on the once aligned view angle coordinates of the preset view angle according to the on-site three-dimensional scanning image of the continuous frame to obtain a final continuous casting digital factory three-dimensional static model; the digital twin model is corrected through the physical data of the field three-dimensional scanning image, so that the accuracy of the model is improved;
in a continuous casting digital factory three-dimensional static model, constructing a continuous casting robot three-dimensional dynamic model, and carrying out visual design on the continuous casting robot three-dimensional dynamic model to obtain the continuous casting digital factory three-dimensional dynamic model provided with a visual interface, comprising the following steps:
constructing a plurality of initial continuous casting robot three-dimensional static models according to equipment drawings of continuous casting robots of different models used in continuous casting reality factories;
According to the position data of the continuous casting robot in the process drawing of the continuous casting plant, adding the initial continuous casting robot three-dimensional static model to the corresponding position of the continuous casting digital plant three-dimensional static model; the position correspondence of the continuous casting robot in a continuous casting reality factory is realized, and the accuracy of a three-dimensional static model of a continuous casting digital factory is improved;
correcting and dynamically converting an initial continuous casting robot three-dimensional static model according to a device three-dimensional scanning video of the continuous casting robot and an action three-dimensional scanning video corresponding to each action gesture to obtain a continuous casting robot three-dimensional dynamic model for dynamically displaying the action gesture of the continuous casting robot, wherein the method comprises the following steps of:
performing frame interception on the equipment three-dimensional scanning video of the continuous casting robot to obtain equipment three-dimensional scanning images of continuous frames;
acquiring view angle coordinates of a field view angle of the equipment according to equipment three-dimensional scanning images of a plurality of frames which are random and discontinuous;
performing secondary alignment on the view angle coordinates of the field view angle of the equipment and the view angle coordinates of the preset view angle after primary alignment of the three-dimensional static model of the continuous casting digital factory to obtain the view angle coordinates of the preset view angle after secondary alignment; the three-dimensional static model of the continuous casting digital factory and the three-dimensional static model of the continuous casting robot are unified in the visual angles of the digital world and the physical world, and the corresponding three-dimensional static model of the continuous casting robot can be observed in the three-dimensional static model of the continuous casting digital factory through the visual angle coordinates of the preset visual angles after secondary alignment;
Correcting the initial continuous casting robot three-dimensional static model based on the view angle coordinates of the preset view angles after secondary alignment according to the equipment three-dimensional scanning images of the continuous frames to obtain a final continuous casting robot three-dimensional static model;
the method comprises the steps of respectively carrying out frame interception on an action three-dimensional scanning video corresponding to each action gesture of the continuous casting robot to obtain an action three-dimensional scanning image of a continuous frame corresponding to each action gesture;
based on the view angle coordinates of the preset view angle after the secondary alignment, respectively carrying out dynamic conversion on the final continuous casting robot three-dimensional static model according to the motion three-dimensional scanning images of the continuous frames corresponding to each motion gesture to obtain a continuous casting robot three-dimensional dynamic model for dynamically displaying the motion gesture of the continuous casting robot; the continuous casting robot three-dimensional dynamic model for dynamically displaying the motion gesture of the continuous casting robot can more intuitively display the motion condition and the working state of the continuous casting robot, and the user experience is improved;
adding a visual management interface to the continuous casting robot three-dimensional dynamic model, and establishing a display link between the visual management interface and equipment operation data and operation work data of the continuous casting robot to obtain a continuous casting digital factory three-dimensional dynamic model provided with the visual interface; the visual management interface can display various data and conditions of the three-dimensional dynamic model of the continuous casting robot in real time, and the equipment operation data and the operation work data are in a format after the code translation, so that any staff who does not understand the code can easily understand the description of the data;
Constructing a continuous casting robot operation detection database, adding the continuous casting robot operation detection database to a continuous casting digital factory three-dimensional dynamic model provided with a visual interface, and obtaining the continuous casting digital factory three-dimensional dynamic model provided with the continuous casting robot operation detection database, wherein the continuous casting digital factory three-dimensional dynamic model comprises the following steps:
establishing a corresponding relation between historical equipment operation data of the continuous casting robot and operation types, adding the corresponding operation types as type labels to the corresponding historical equipment operation data to obtain a plurality of historical equipment operation data provided with the type labels;
establishing a corresponding relation between historical operation work data of each operation work type and a preset operation work threshold;
training by using an Elman neural network algorithm in a machine learning algorithm according to a plurality of historical equipment operation data provided with type labels, and constructing a continuous casting robot operation work recognition model; model training is carried out through a large number of training samples provided with type labels, the Elman neural network learns the data characteristics of a plurality of historical equipment operation data through a neuron connection structure of the Elman neural network, when new equipment operation data is input, the corresponding type labels can be accurately output through a probability distribution prediction mode, and operation work type prediction of the continuous casting robot is realized, for example, an A arm of the continuous casting robot is at an X1 point location, a B arm of the continuous casting robot is at a Y2 point location, and at the moment, the continuous casting robot is being utilized for testing the temperature of molten steel in a big ladle;
Training by using an Elman neural network algorithm of a machine learning algorithm according to a plurality of historical equipment operation data provided with fault labels, and constructing a continuous casting robot fault diagnosis model; model training is carried out through a large number of training samples provided with fault labels, the Elman neural network algorithm learns the data characteristics of a plurality of historical equipment operation data through the neuron connection structure of the Elman neural network algorithm, when new equipment operation data is input, the corresponding fault labels can be accurately output through a probability distribution prediction mode, the fault diagnosis of the continuous casting robot is realized,
the equipment operation data comprise voltage data, current data, power data, position data of each moving part and the like of the continuous casting robot operation, the equipment operation data can be used for judging the working state and the action condition of the equipment operation data, when the continuous casting robot is in an abnormal or fault working state, the voltage data, the current data, the power data and the like of the equipment operation data have large differences from the normal working state, the action condition of the equipment operation data, namely the current operation working type of the continuous casting robot operation, can be judged according to the corresponding operation working data, for example, the temperature data collected by the molten steel temperature work in a test ladle of the continuous casting robot, and can be used for judging whether the current operation work is qualified or not when the accurate operation working type is acquired;
Collecting historical equipment operation data, historical operation work data, model metadata of a continuous casting robot operation work identification model and model metadata of a continuous casting robot fault diagnosis model, constructing a continuous casting robot operation detection database, and adding the continuous casting robot operation detection database to a continuous casting digital factory three-dimensional dynamic model provided with a visual interface;
establishing a visual management interface of the continuous casting digital plant three-dimensional dynamic model and a display link of the continuous casting robot fault diagnosis model and a visual management interface of the continuous casting digital plant three-dimensional dynamic model and a display link of the continuous casting robot fault diagnosis model to obtain the continuous casting digital plant three-dimensional dynamic model provided with a continuous casting robot operation detection database;
the method comprises the steps of collecting equipment operation data and operation work data of the continuous casting robot in real time, and managing the continuous casting robot by using a continuous casting digital factory three-dimensional dynamic model provided with a continuous casting robot operation detection database according to the real-time equipment operation data and the real-time operation work data, and comprises the following steps:
collecting equipment operation data and operation work data of the continuous casting robot in real time, and storing the real-time equipment operation data and the real-time operation work data into an operation detection database of the continuous casting robot;
Calling a continuous casting robot fault diagnosis model in a continuous casting robot operation detection database to carry out fault diagnosis according to real-time equipment operation data, obtaining a fault diagnosis result of the continuous casting robot, and displaying the real-time equipment operation data and the fault diagnosis result on a visual management interface;
according to the real-time operation data, calling a continuous casting robot operation recognition model in a continuous casting robot operation detection database to perform operation recognition to obtain an operation type of the continuous casting robot, and displaying the real-time operation data and the operation type on a visual management interface;
according to the real-time operation work data and the operation work type thereof, matching the historical operation work data of the corresponding operation work type, according to the corresponding relation between the historical operation work data of the operation work type and the preset operation work threshold value, comparing the real-time operation work data with the preset operation work threshold value to obtain the operation work condition of the continuous casting robot, and displaying the operation work condition on a visual management interface; for example, if the temperature of molten steel in a large ladle tested by the continuous casting robot exceeds a preset operation working threshold, the operation working condition of the continuous casting robot is about to stop working, and a patrol personnel is required to maintain or a worker checks actual temperature data to judge whether to restart the continuous casting robot;
The staff can observe the visual management interface of each continuous casting robot three-dimensional dynamic model through the visual continuous casting digital factory three-dimensional static model, realize that information such as equipment operation data, fault diagnosis result, operation work data, operation work type and operation work condition are convenient to know, can also present equipment operation data, operation work data etc. to the staff through the mode of trend chart, realize the visualization of continuous casting robot management, and send alarm signal when continuous casting robot breaks down, remind the staff to maintain.
Examples
As shown in fig. 2, the present embodiment provides a continuous casting robot management system based on digital twinning, for implementing the continuous casting robot management method in embodiment 1, where the system includes a model building unit, a database building unit, and a management application unit, the model building unit, the database building unit, and the management application unit are sequentially connected, and the management application unit, the database building unit, and the model building unit are all connected with an external factory data server;
the model construction unit is used for extracting a building drawing and an on-site three-dimensional scanning video of the continuous casting reality factory, which are stored by the factory data server, and an equipment drawing, an equipment three-dimensional scanning video and an action three-dimensional scanning video of the continuous casting robot, constructing a continuous casting digital factory three-dimensional static model according to a process drawing and an on-site three-dimensional scanning video of the continuous casting factory, constructing a continuous casting robot three-dimensional dynamic model in the continuous casting digital factory three-dimensional static model according to the equipment drawing, the equipment three-dimensional scanning video and the action three-dimensional scanning video of the continuous casting robot, and carrying out visual design on the continuous casting robot three-dimensional dynamic model to obtain the continuous casting digital factory three-dimensional dynamic model provided with a visual interface;
The database construction unit is used for extracting historical equipment operation data and historical operation work data of the continuous casting robot stored by the factory data server, constructing a continuous casting robot operation detection database according to the historical equipment operation data and the historical operation work data of the continuous casting robot, and adding the continuous casting robot operation detection database to the continuous casting digital factory three-dimensional dynamic model provided with the visual interface to obtain the continuous casting digital factory three-dimensional dynamic model provided with the continuous casting robot operation detection database;
the management application unit is used for rendering the continuous casting digital factory three-dimensional dynamic model provided with the continuous casting robot operation detection database, extracting real-time equipment operation data and real-time operation work data stored by the factory data server, and managing the continuous casting robot by using the continuous casting digital factory three-dimensional dynamic model provided with the continuous casting robot operation detection database according to the real-time equipment operation data and the real-time operation work data.
Preferably, the model building unit comprises a static model building module, a dynamic model building module and a visual design module, wherein the static model building module, the dynamic model building module and the visual design module are sequentially connected, the static model building module and the dynamic model building module are connected with an external factory data server, and the visual design module is connected with the database building unit;
The static model construction module is used for extracting a building drawing and a field three-dimensional scanning video of the continuous casting reality factory stored by the factory data server, constructing an initial continuous casting digital factory three-dimensional static model according to a process drawing of the continuous casting factory, correcting the initial continuous casting digital factory three-dimensional static model according to the field three-dimensional scanning video of the continuous casting reality factory to obtain a final continuous casting digital factory three-dimensional static model, extracting an equipment drawing, an equipment three-dimensional scanning video and an action three-dimensional scanning video of the continuous casting robot stored by the factory data server, constructing an initial continuous casting robot three-dimensional static model according to the equipment drawing of the continuous casting robot, and adding the initial continuous casting robot three-dimensional static model to a corresponding position of the continuous casting digital factory three-dimensional static model according to position data of the continuous casting robot in the process drawing of the continuous casting factory;
the dynamic model construction module is used for correcting and dynamically converting the initial continuous casting robot three-dimensional static model according to the equipment three-dimensional scanning video of the continuous casting robot and the action three-dimensional scanning video corresponding to each action gesture to obtain a continuous casting robot three-dimensional dynamic model for dynamically displaying the action gesture of the continuous casting robot;
The visual design module is used for adding a visual management interface to the continuous casting robot three-dimensional dynamic model, establishing a display link between the visual management interface and equipment operation data and operation work data of the continuous casting robot, obtaining a continuous casting digital factory three-dimensional dynamic model provided with the visual interface, and sending the continuous casting digital factory three-dimensional dynamic model provided with the visual interface to the database construction unit.
Preferably, the database construction unit comprises a corresponding relation establishment module, a continuous casting robot operation work identification model construction module, a continuous casting robot fault diagnosis model construction module, a continuous casting robot operation detection database construction module and a visual linkage module, wherein the corresponding relation establishment module, the continuous casting robot operation work identification model construction module, the continuous casting robot fault diagnosis model construction module, the continuous casting robot operation detection database construction module and the visual linkage module are sequentially connected, and the corresponding relation establishment module is respectively connected with the model construction unit and an external factory data server, and the visual linkage module is connected with the management application unit;
the corresponding relation establishing module is used for receiving the continuous casting digital factory three-dimensional dynamic model provided with the visual interface and sent by the model constructing unit, extracting the historical equipment operation data of the continuous casting robot and the historical operation work data stored by the factory data server, establishing the corresponding relation between the historical equipment operation data of the continuous casting robot and the operation work types, taking the corresponding operation work types as type labels, adding the type labels to the corresponding historical equipment operation data to obtain a plurality of historical equipment operation data provided with the type labels, and establishing the corresponding relation between the historical operation work data of each operation work type and a preset operation work threshold;
The continuous casting robot operation work recognition model construction module is used for training by using a machine learning algorithm according to a plurality of historical equipment operation data provided with type labels to construct a continuous casting robot operation work recognition model;
the continuous casting robot fault diagnosis model construction module is used for training by using a machine learning algorithm according to a plurality of historical equipment operation data provided with fault labels to construct a continuous casting robot fault diagnosis model;
the continuous casting robot operation detection database construction module is used for collecting historical equipment operation data, historical operation work data, model metadata of a continuous casting robot operation work identification model and model metadata of a continuous casting robot fault diagnosis model, constructing a continuous casting robot operation detection database, and adding the continuous casting robot operation detection database to a continuous casting digital factory three-dimensional dynamic model provided with a visual interface;
the visual linkage module is used for establishing a visual management interface of the continuous casting digital plant three-dimensional dynamic model and a display link of the continuous casting robot fault diagnosis model and a visual management interface of the continuous casting digital plant three-dimensional dynamic model and a display link of the continuous casting robot fault diagnosis model, obtaining the continuous casting digital plant three-dimensional dynamic model provided with the continuous casting robot operation detection database, and sending model metadata of the continuous casting digital plant three-dimensional dynamic model provided with the continuous casting robot operation detection database to the management application unit.
Preferably, the management application unit comprises a model rendering module, a real-time data storage module, a fault diagnosis module, an operation work identification module and an operation work condition judging module, wherein the model rendering module, the real-time data storage module, the fault diagnosis module, the operation work identification module and the operation work condition judging module are sequentially connected, the model rendering module is connected with the database construction unit, and the real-time data storage module is connected with an external factory data server;
the model rendering module is used for rendering according to the model metadata of the continuous casting digital factory three-dimensional dynamic model provided with the continuous casting robot operation detection database and sent by the database construction unit, so as to obtain a rendered continuous casting digital factory three-dimensional dynamic model provided with the continuous casting robot operation detection database;
a real-time data storage module for extracting real-time equipment operation data and real-time operation work data stored in the factory data server,
the continuous casting digital factory three-dimensional dynamic model is constructed by the rendering model construction unit and the database construction unit and is provided with a continuous casting robot operation detection database, real-time equipment operation data and real-time operation work data stored by a factory data server are extracted, and the real-time equipment operation data and the real-time operation work data are stored in the continuous casting robot operation detection database;
The fault diagnosis module is used for establishing a continuous casting robot fault diagnosis model according to model metadata of the continuous casting robot fault diagnosis model in the continuous casting robot operation detection database, calling the continuous casting robot fault diagnosis model in the continuous casting robot operation detection database to carry out fault diagnosis according to real-time equipment operation data to obtain a fault diagnosis result of the continuous casting robot, and displaying the real-time equipment operation data and the fault diagnosis result on the visual management interface;
the operation work identification module is used for establishing a continuous casting robot operation work identification model according to model metadata of the continuous casting robot operation work identification model in the continuous casting robot operation detection database, calling the continuous casting robot operation work identification model in the continuous casting robot operation detection database to conduct operation work identification according to real-time operation work data to obtain an operation work type of the continuous casting robot, and displaying the real-time operation work data and the operation work type on the visual management interface;
the operation working condition judging module is used for matching the historical operation working data of the corresponding operation working type according to the real-time operation working data and the operation working type thereof, comparing the real-time operation working data with a preset operation working threshold value according to the corresponding relation between the historical operation working data of the operation working type and the preset operation working threshold value to obtain the operation working condition of the continuous casting robot, and displaying the operation working condition on the visual management interface.
According to the continuous casting robot management method and system based on digital twin, the overall situation of a continuous casting reality factory is simulated based on the three-dimensional static model of the continuous casting digital factory, the user immersive experience degree is improved, the continuous casting robot is visually managed through the three-dimensional dynamic model of the continuous casting robot, the situation that the continuous casting robot is manually analyzed on site is avoided, the labor cost investment is reduced, the safety is improved, the continuous casting robot operation detection database is built and used for storing historical or real-time equipment operation data and operation work data, data support is provided for continuous casting robot operation situation analysis, the accuracy of the model and the data is improved, the observation and investigation of the continuous casting robot are avoided, the operation work recognition and fault diagnosis functions are provided, the intelligent degree and convenience of management are improved, the operation situation and the operation state of the continuous casting robot can be visually and conveniently observed through the visual interface, and the specific situation of data expression is intuitively understood, and the user experience and the system practicability are improved.
The invention is not limited to the alternative embodiments described above, but any person may derive other various forms of products in the light of the present invention. The above detailed description should not be construed as limiting the scope of the invention, which is defined in the claims and the description may be used to interpret the claims.
Claims (10)
1. A continuous casting robot management method based on digital twinning is characterized in that: the method comprises the following steps:
constructing a continuous casting digital factory three-dimensional static model;
constructing a continuous casting robot three-dimensional dynamic model in a continuous casting digital factory three-dimensional static model, and performing visual design on the continuous casting robot three-dimensional dynamic model to obtain the continuous casting digital factory three-dimensional dynamic model provided with a visual interface;
constructing a continuous casting robot operation detection database, and adding the continuous casting robot operation detection database to the continuous casting digital factory three-dimensional dynamic model provided with the visual interface to obtain the continuous casting digital factory three-dimensional dynamic model provided with the continuous casting robot operation detection database;
and acquiring equipment operation data and operation work data of the continuous casting robot in real time, and managing the continuous casting robot by using a continuous casting digital factory three-dimensional dynamic model provided with a continuous casting robot operation detection database according to the real-time equipment operation data and the real-time operation work data.
2. The continuous casting robot management method based on digital twinning according to claim 1, wherein: the method for constructing the continuous casting digital factory three-dimensional static model comprises the following steps:
Constructing an initial continuous casting digital factory three-dimensional static model according to a process drawing of a continuous casting factory;
correcting the initial continuous casting digital factory three-dimensional static model according to the site three-dimensional scanning video of the continuous casting reality factory to obtain a final continuous casting digital factory three-dimensional static model;
correcting the initial continuous casting digital factory three-dimensional static model according to the on-site three-dimensional scanning video of the continuous casting real factory to obtain the final continuous casting digital factory three-dimensional static model, comprising the following steps:
performing frame interception on the site three-dimensional scanning video of the continuous casting reality factory to obtain site three-dimensional scanning images of continuous frames;
acquiring view angle coordinates of a factory site view angle according to site three-dimensional scanning images of a plurality of frames which are random and discontinuous;
aligning the view angle coordinates of the factory site view angle with the view angle coordinates of the preset view angle of the initial continuous casting digital factory three-dimensional static model for one time to obtain the view angle coordinates of the preset view angle after one time alignment;
and correcting the initial continuous casting digital factory three-dimensional static model according to the on-site three-dimensional scanning image of the continuous frame based on the once aligned visual angle coordinates of the preset visual angle to obtain the final continuous casting digital factory three-dimensional static model.
3. The continuous casting robot management method based on digital twinning according to claim 2, wherein: in a continuous casting digital factory three-dimensional static model, constructing a continuous casting robot three-dimensional dynamic model, and carrying out visual design on the continuous casting robot three-dimensional dynamic model to obtain the continuous casting digital factory three-dimensional dynamic model provided with a visual interface, comprising the following steps:
constructing an initial continuous casting robot three-dimensional static model according to the equipment drawing of the continuous casting robot;
according to the position data of the continuous casting robot in the process drawing of the continuous casting plant, adding the initial continuous casting robot three-dimensional static model to the corresponding position of the continuous casting digital plant three-dimensional static model;
correcting and dynamically converting the initial continuous casting robot three-dimensional static model according to the equipment three-dimensional scanning video of the continuous casting robot and the action three-dimensional scanning video corresponding to each action gesture to obtain a continuous casting robot three-dimensional dynamic model for dynamically displaying the action gesture of the continuous casting robot;
and adding a visual management interface into the three-dimensional dynamic model of the continuous casting robot, and establishing a display link between the visual management interface and equipment operation data and operation work data of the continuous casting robot to obtain the three-dimensional dynamic model of the continuous casting digital factory provided with the visual interface.
4. A continuous casting robot management method based on digital twinning according to claim 3, characterized in that: correcting and dynamically converting an initial continuous casting robot three-dimensional static model according to a device three-dimensional scanning video of the continuous casting robot, a motion three-dimensional scanning video corresponding to each motion gesture and historical device operation data to obtain a continuous casting robot three-dimensional dynamic model for dynamically displaying the motion gesture of the continuous casting robot, wherein the method comprises the following steps:
performing frame interception on the equipment three-dimensional scanning video of the continuous casting robot to obtain equipment three-dimensional scanning images of continuous frames;
acquiring view angle coordinates of a field view angle of the equipment according to equipment three-dimensional scanning images of a plurality of frames which are random and discontinuous;
performing secondary alignment on the view angle coordinates of the field view angle of the equipment and the view angle coordinates of the preset view angle after primary alignment of the three-dimensional static model of the continuous casting digital factory to obtain the view angle coordinates of the preset view angle after secondary alignment;
correcting the initial continuous casting robot three-dimensional static model based on the view angle coordinates of the preset view angles after secondary alignment according to the equipment three-dimensional scanning images of the continuous frames to obtain a final continuous casting robot three-dimensional static model;
The method comprises the steps of respectively carrying out frame interception on an action three-dimensional scanning video corresponding to each action gesture of the continuous casting robot to obtain an action three-dimensional scanning image of a continuous frame corresponding to each action gesture;
and based on the view angle coordinates of the preset view angle after the secondary alignment, respectively carrying out dynamic conversion on the final continuous casting robot three-dimensional static model according to the motion three-dimensional scanning images of the continuous frames corresponding to each motion gesture, and obtaining the continuous casting robot three-dimensional dynamic model for dynamically displaying the motion gesture of the continuous casting robot.
5. The continuous casting robot management method based on digital twinning according to claim 1, wherein: constructing a continuous casting robot operation detection database, adding the continuous casting robot operation detection database to a continuous casting digital factory three-dimensional dynamic model provided with a visual interface, and obtaining the continuous casting digital factory three-dimensional dynamic model provided with the continuous casting robot operation detection database, wherein the continuous casting digital factory three-dimensional dynamic model comprises the following steps:
establishing a corresponding relation between historical equipment operation data of the continuous casting robot and operation types, adding the corresponding operation types as type labels to the corresponding historical equipment operation data to obtain a plurality of historical equipment operation data provided with the type labels;
Establishing a corresponding relation between historical operation work data of each operation work type and a preset operation work threshold;
training by using a machine learning algorithm according to a plurality of historical equipment operation data provided with type labels, and constructing a continuous casting robot operation work recognition model;
training by using a machine learning algorithm according to a plurality of historical equipment operation data provided with fault labels, and constructing a continuous casting robot fault diagnosis model;
collecting historical equipment operation data, historical operation work data, model metadata of a continuous casting robot operation work identification model and model metadata of a continuous casting robot fault diagnosis model, constructing a continuous casting robot operation detection database, and adding the continuous casting robot operation detection database to a continuous casting digital factory three-dimensional dynamic model provided with a visual interface;
and establishing a visual management interface of the continuous casting digital plant three-dimensional dynamic model and a display link of the continuous casting robot fault diagnosis model, and a visual management interface of the continuous casting digital plant three-dimensional dynamic model and a display link of the continuous casting robot fault diagnosis model to obtain the continuous casting digital plant three-dimensional dynamic model provided with the continuous casting robot operation detection database.
6. The continuous casting robot management method based on digital twinning according to claim 5, wherein: the method comprises the steps of collecting equipment operation data and operation work data of the continuous casting robot in real time, and managing the continuous casting robot by using a continuous casting digital factory three-dimensional dynamic model provided with a continuous casting robot operation detection database according to the real-time equipment operation data and the real-time operation work data, and comprises the following steps:
collecting equipment operation data and operation work data of the continuous casting robot in real time, and storing the real-time equipment operation data and the real-time operation work data into an operation detection database of the continuous casting robot;
calling a continuous casting robot fault diagnosis model in a continuous casting robot operation detection database to carry out fault diagnosis according to real-time equipment operation data, obtaining a fault diagnosis result of the continuous casting robot, and displaying the real-time equipment operation data and the fault diagnosis result on a visual management interface;
according to the real-time operation data, calling a continuous casting robot operation recognition model in a continuous casting robot operation detection database to perform operation recognition to obtain an operation type of the continuous casting robot, and displaying the real-time operation data and the operation type on a visual management interface;
According to the real-time operation work data and the operation work types thereof, matching the historical operation work data of the corresponding operation work types, according to the corresponding relation between the historical operation work data of the operation work types and the preset operation work threshold, comparing the real-time operation work data with the preset operation work threshold in a numerical mode to obtain the operation work condition of the continuous casting robot, and displaying the operation work condition on a visual management interface.
7. A continuous casting robot management system based on digital twinning, for implementing the continuous casting robot management method as claimed in any one of claims 1 to 6, characterized in that: the system comprises a model building unit, a database building unit and a management application unit, wherein the model building unit, the database building unit and the management application unit are sequentially connected, and the management application unit, the database building unit and the model building unit are all connected with an external factory data server;
the model construction unit is used for extracting a process drawing and an on-site three-dimensional scanning video of the continuous casting plant, which are stored by the plant data server, and an equipment drawing, an equipment three-dimensional scanning video and an action three-dimensional scanning video of the continuous casting robot, constructing a continuous casting digital plant three-dimensional static model according to the process drawing and the on-site three-dimensional scanning video of the continuous casting plant, constructing a continuous casting robot three-dimensional dynamic model in the continuous casting digital plant three-dimensional static model according to the equipment drawing, the equipment three-dimensional scanning video and the action three-dimensional scanning video of the continuous casting robot, and carrying out visual design on the continuous casting robot three-dimensional dynamic model to obtain the continuous casting digital plant three-dimensional dynamic model provided with a visual interface;
The database construction unit is used for extracting historical equipment operation data and historical operation work data of the continuous casting robot stored by the factory data server, constructing a continuous casting robot operation detection database according to the historical equipment operation data and the historical operation work data of the continuous casting robot, and adding the continuous casting robot operation detection database to the continuous casting digital factory three-dimensional dynamic model provided with the visual interface to obtain the continuous casting digital factory three-dimensional dynamic model provided with the continuous casting robot operation detection database;
the management application unit is used for rendering the continuous casting digital factory three-dimensional dynamic model provided with the continuous casting robot operation detection database, extracting real-time equipment operation data and real-time operation work data stored by the factory data server, and managing the continuous casting robot by using the continuous casting digital factory three-dimensional dynamic model provided with the continuous casting robot operation detection database according to the real-time equipment operation data and the real-time operation work data.
8. The digital twinning-based continuous casting robot management system according to claim 7, wherein: the model building unit comprises a static model building module, a dynamic model building module and a visual design module, wherein the static model building module, the dynamic model building module and the visual design module are sequentially connected, the static model building module and the dynamic model building module are connected with an external factory data server, and the visual design module is connected with the database building unit;
The static model construction module is used for extracting a process drawing and a field three-dimensional scanning video of the continuous casting plant stored by the plant data server, constructing an initial continuous casting digital plant three-dimensional static model according to the process drawing of the continuous casting plant, correcting the initial continuous casting digital plant three-dimensional static model according to the field three-dimensional scanning video of the continuous casting real plant to obtain a final continuous casting digital plant three-dimensional static model, extracting an equipment drawing, an equipment three-dimensional scanning video and an action three-dimensional scanning video of the continuous casting robot stored by the plant data server, constructing an initial continuous casting robot three-dimensional static model according to the equipment drawing of the continuous casting robot, and adding the initial continuous casting robot three-dimensional static model to a corresponding position of the continuous casting digital plant three-dimensional static model according to the position data of the continuous casting robot in the process drawing of the continuous casting plant;
the dynamic model construction module is used for correcting and dynamically converting the initial continuous casting robot three-dimensional static model according to the equipment three-dimensional scanning video of the continuous casting robot and the action three-dimensional scanning video corresponding to each action gesture to obtain a continuous casting robot three-dimensional dynamic model for dynamically displaying the action gesture of the continuous casting robot;
The visual design module is used for adding a visual management interface to the continuous casting robot three-dimensional dynamic model, establishing a display link between the visual management interface and equipment operation data and operation work data of the continuous casting robot, obtaining a continuous casting digital factory three-dimensional dynamic model provided with the visual interface, and sending the continuous casting digital factory three-dimensional dynamic model provided with the visual interface to the database construction unit.
9. The digital twinning-based continuous casting robot management system according to claim 7, wherein: the database construction unit comprises a corresponding relation establishment module, a continuous casting robot operation work identification model construction module, a continuous casting robot fault diagnosis model construction module, a continuous casting robot operation detection database construction module and a visual linkage module, wherein the corresponding relation establishment module, the continuous casting robot operation work identification model construction module, the continuous casting robot fault diagnosis model construction module, the continuous casting robot operation detection database construction module and the visual linkage module are sequentially connected, and the corresponding relation establishment module is respectively connected with the model construction unit and an external factory data server, and the visual linkage module is connected with the management application unit;
The corresponding relation establishing module is used for receiving the continuous casting digital factory three-dimensional dynamic model provided with the visual interface and sent by the model constructing unit, extracting the historical equipment operation data of the continuous casting robot and the historical operation work data stored by the factory data server, establishing the corresponding relation between the historical equipment operation data of the continuous casting robot and the operation work types, taking the corresponding operation work types as type labels, adding the type labels to the corresponding historical equipment operation data to obtain a plurality of historical equipment operation data provided with the type labels, and establishing the corresponding relation between the historical operation work data of each operation work type and a preset operation work threshold;
the continuous casting robot operation work recognition model construction module is used for training by using a machine learning algorithm according to a plurality of historical equipment operation data provided with type labels to construct a continuous casting robot operation work recognition model;
the continuous casting robot fault diagnosis model construction module is used for training by using a machine learning algorithm according to a plurality of historical equipment operation data provided with fault labels to construct a continuous casting robot fault diagnosis model;
the continuous casting robot operation detection database construction module is used for collecting historical equipment operation data, historical operation work data, model metadata of a continuous casting robot operation work identification model and model metadata of a continuous casting robot fault diagnosis model, constructing a continuous casting robot operation detection database, and adding the continuous casting robot operation detection database to a continuous casting digital factory three-dimensional dynamic model provided with a visual interface;
The visual linkage module is used for establishing a visual management interface of the continuous casting digital plant three-dimensional dynamic model and a display link of the continuous casting robot fault diagnosis model and a visual management interface of the continuous casting digital plant three-dimensional dynamic model and a display link of the continuous casting robot fault diagnosis model, obtaining the continuous casting digital plant three-dimensional dynamic model provided with the continuous casting robot operation detection database, and sending model metadata of the continuous casting digital plant three-dimensional dynamic model provided with the continuous casting robot operation detection database to the management application unit.
10. The digital twinning-based continuous casting robot management system according to claim 7, wherein: the management application unit comprises a model rendering module, a real-time data storage module, a fault diagnosis module, an operation work identification module and an operation work condition judging module, wherein the model rendering module, the real-time data storage module, the fault diagnosis module, the operation work identification module and the operation work condition judging module are sequentially connected, the model rendering module is connected with the database construction unit, and the real-time data storage module is connected with an external factory data server;
The model rendering module is used for rendering according to the model metadata of the continuous casting digital factory three-dimensional dynamic model provided with the continuous casting robot operation detection database and sent by the database construction unit, so as to obtain a rendered continuous casting digital factory three-dimensional dynamic model provided with the continuous casting robot operation detection database;
a real-time data storage module for extracting real-time equipment operation data and real-time operation work data stored in the factory data server,
the continuous casting digital factory three-dimensional dynamic model is constructed by the rendering model construction unit and the database construction unit and is provided with a continuous casting robot operation detection database, real-time equipment operation data and real-time operation work data stored by a factory data server are extracted, and the real-time equipment operation data and the real-time operation work data are stored in the continuous casting robot operation detection database;
the fault diagnosis module is used for establishing a continuous casting robot fault diagnosis model according to model metadata of the continuous casting robot fault diagnosis model in the continuous casting robot operation detection database, calling the continuous casting robot fault diagnosis model in the continuous casting robot operation detection database to carry out fault diagnosis according to real-time equipment operation data to obtain a fault diagnosis result of the continuous casting robot, and displaying the real-time equipment operation data and the fault diagnosis result on the visual management interface;
The operation work identification module is used for establishing a continuous casting robot operation work identification model according to model metadata of the continuous casting robot operation work identification model in the continuous casting robot operation detection database, calling the continuous casting robot operation work identification model in the continuous casting robot operation detection database to conduct operation work identification according to real-time operation work data to obtain an operation work type of the continuous casting robot, and displaying the real-time operation work data and the operation work type on the visual management interface;
the operation working condition judging module is used for matching the historical operation working data of the corresponding operation working type according to the real-time operation working data and the operation working type thereof, comparing the real-time operation working data with a preset operation working threshold value according to the corresponding relation between the historical operation working data of the operation working type and the preset operation working threshold value to obtain the operation working condition of the continuous casting robot, and displaying the operation working condition on the visual management interface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310285814.3A CN116277001A (en) | 2023-03-22 | 2023-03-22 | Continuous casting robot management method and system based on digital twin |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310285814.3A CN116277001A (en) | 2023-03-22 | 2023-03-22 | Continuous casting robot management method and system based on digital twin |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116277001A true CN116277001A (en) | 2023-06-23 |
Family
ID=86825454
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310285814.3A Pending CN116277001A (en) | 2023-03-22 | 2023-03-22 | Continuous casting robot management method and system based on digital twin |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116277001A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117475431A (en) * | 2023-12-27 | 2024-01-30 | 君华高科集团有限公司 | Food safety supervision method and system based on digital twin technology |
-
2023
- 2023-03-22 CN CN202310285814.3A patent/CN116277001A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117475431A (en) * | 2023-12-27 | 2024-01-30 | 君华高科集团有限公司 | Food safety supervision method and system based on digital twin technology |
| CN117475431B (en) * | 2023-12-27 | 2024-03-15 | 君华高科集团有限公司 | Food safety supervision method and system based on digital twin technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107529667B (en) | Mixed reality nuclear power plant simulation and analysis system | |
| CN111722714A (en) | Digital substation metering operation inspection auxiliary method based on AR technology | |
| CN107730017A (en) | Intelligent metallurgical equipment operational diagnostics system | |
| CN113689013A (en) | Intelligent monitoring and operation and maintenance system for transformer | |
| CN112290546B (en) | Transformer substation primary equipment fault discrimination method based on man-machine co-fusion | |
| CN111850609B (en) | Aluminum electrolysis control system based on digital twinning | |
| CN116277001A (en) | Continuous casting robot management method and system based on digital twin | |
| CN112859769B (en) | Energy consumption monitoring device in intelligent production equipment and operation method thereof | |
| CN116772868B (en) | Distribution room inspection robot and automatic inspection method thereof | |
| CN115184361A (en) | Real-time workpiece surface defect detection and evaluation system and method based on machine vision | |
| CN111652406A (en) | Method and system for predicting running state of power grid equipment under cloud-edge cooperation | |
| CN110728381A (en) | Intelligent power plant inspection method and system based on RFID and data processing | |
| CN116541570A (en) | Equipment predictive maintenance system based on digital twinning | |
| CN116418117A (en) | Equipment detection system for intelligent power grid | |
| CN111474870A (en) | Fault diagnosis and detection system based on machine learning | |
| CN117235443A (en) | Electric power operation safety monitoring method and system based on edge AI | |
| CN116147697B (en) | Unattended monitoring method and system for aluminum hydroxide | |
| CN111668935A (en) | Substation operation preparation management method and system based on EIM | |
| CN114049697B (en) | Inspection auxiliary system | |
| CN112113145A (en) | Intelligent online detection method for chemical pipeline safety | |
| CN111258431B (en) | Turbine maintenance auxiliary system based on mixed reality | |
| CN109494882B (en) | Method and system for diagnosing state of substation switch equipment | |
| CN112936342A (en) | System and method for evaluating actions of entity robot based on human body posture recognition algorithm | |
| CN214335512U (en) | Visual management system of electrical equipment | |
| CN117077040B (en) | Large-scale complex equipment fault diagnosis and prediction system based on machine learning |
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 |