CN113609672A - Incremental model-based digital twin system coevolution method - Google Patents
Incremental model-based digital twin system coevolution method Download PDFInfo
- Publication number
- CN113609672A CN113609672A CN202110883308.5A CN202110883308A CN113609672A CN 113609672 A CN113609672 A CN 113609672A CN 202110883308 A CN202110883308 A CN 202110883308A CN 113609672 A CN113609672 A CN 113609672A
- Authority
- CN
- China
- Prior art keywords
- digital twin
- model
- twin system
- data
- processing
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000012545 processing Methods 0.000 claims abstract description 44
- 230000008569 process Effects 0.000 claims abstract description 37
- 238000003754 machining Methods 0.000 claims abstract description 11
- 230000003993 interaction Effects 0.000 claims abstract description 5
- 238000012544 monitoring process Methods 0.000 claims description 8
- 238000013461 design Methods 0.000 claims description 7
- 238000007689 inspection Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000009825 accumulation Methods 0.000 claims description 5
- 238000013145 classification model Methods 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 abstract description 14
- 206010063385 Intellectualisation Diseases 0.000 abstract 1
- 238000004458 analytical method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0633—Workflow analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/18—Manufacturability analysis or optimisation for manufacturability
-
- 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
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Marketing (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Manufacturing & Machinery (AREA)
- Computer Hardware Design (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Primary Health Care (AREA)
- Geometry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- General Factory Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a digital twin system co-evolution method based on an incremental model, and belongs to the technical field of intelligent manufacturing. A digital twin system coevolution method based on an incremental model comprises the following steps: s1, generating digital twin data in the machining process by means of data interaction between the twin model and the physical entity based on a known digital twin system; s2, collecting and analyzing various state variable quantities in the machining process, and acquiring data related to a decision model in the digital twin system; s3, the digital twin system is assisted to make a decision by combining an intelligent algorithm according to the historical data of the state variation in the S2; s4, in the processing process, historical data of the same scene are transmitted to the digital twin system through the cloud platform, and the co-evolution of the digital twin system is promoted; the invention better realizes the intellectualization of numerical control processing and effectively improves the precision and the efficiency of a mechanical processing system in the industrial operation process.
Description
Technical Field
The invention relates to the technical field of intelligent manufacturing, in particular to a digital twin system coevolution method based on an incremental model.
Background
The digital twin technology as a breakthrough technology provides a great impetus for this, which has the potential to change the aspects of today and future manufacturing. The digital twin, as a mirror of the real world, provides a means to simulate, predict, and optimize physical manufacturing systems and processes. The digital twin and intelligent algorithm can be used for realizing the operation monitoring and optimization of data driving, developing innovative products and services, improving the processing efficiency and ensuring the processing quality. Although research has reported potential application prospects of digital twins in the manufacturing industry, the current method for realizing digital twins in the manufacturing field lacks deep knowledge of concepts, frameworks and development methods of digital twins, and hinders the development of the application of digital twins in intelligent manufacturing.
Because the actual industrial process is in constant change, the system cannot identify new classes that are derived from the training sample set and cannot be characterized. The traditional decision model lacks a corresponding recognition mechanism, and can only classify the new class samples into known classes, resulting in wrong classification results. When a new category problem occurs, the incremental learning method firstly utilizes expert knowledge to mark the new category problem, and the real category of the new category problem is determined; and then, utilizing the marked sample to update the classification model in an off-line manner, and continuously putting the updated model into online use. It is worth noting that many practical industrial processes (particularly process industrial processes) are often required to remain continuously operating for extended periods of time, subject to production requirements. Incremental learning is not suitable for practical industrial processes with high real-time and long continuity, since offline labeling of samples and offline updating of models takes a long time. In other words, if a new type of sample can be identified in an online manner, the method has important significance for process diagnosis of an actual industrial process, and in view of this, a digital twin system co-evolution method based on an incremental model is provided.
Disclosure of Invention
The invention aims to solve the technical problem of providing a digital twin system co-evolution method based on an incremental model, and provides an effective realization idea for intelligentizing a numerical control processing system and improving the system precision.
In order to achieve the purpose, the invention adopts the following technical scheme:
a digital twin system coevolution method based on an incremental model specifically comprises the following steps:
s1, generating digital twin data in the machining process by means of data interaction between the twin model and the physical entity based on a known digital twin system;
s2, collecting and analyzing various state variable quantities in the machining process, and acquiring data related to a decision model in the digital twin system;
s3, the digital twin system is assisted to make a decision by combining an intelligent algorithm according to the historical data of the state variation in the S2;
and S4, in the processing process, historical data of the same scene is transmitted to the digital twin system through the cloud platform, and the co-evolution of the digital twin system is promoted.
Preferably, the digital twin system mentioned in S1-S4 includes a digital twin process design unit, a processing monitoring unit and a processing quality inspection unit, and the digital twin process design unit, the processing monitoring unit and the processing quality inspection unit build corresponding databases through data accumulation during working.
Preferably, as the processing cases accumulate, the samples are marked off-line to update the classification model, and then the updated model is put into online use again.
Preferably, in the co-evolution process, the step of updating the model in a co-ordinated manner is as follows:
a1, defining important parameters in the updating mode, including a sharing parameter thetasTask specific parameter θ for each old taskoTraining data and truth X for new tasksnAnd Yn。
A2, model initialization, comprising: computing the output Y of an old task for new datao←CNN(Xn，θs，θo) (ii) a Randomly initializing a new parameter thetan←RANDINIT(|θn|)；
A3, model training, including defining old task output as
Define new task output as
The objective function is:
compared with the prior art, the invention provides a digital twin system co-evolution method based on an incremental model, which has the following beneficial effects:
the invention is based on the self-adaptive evolution function of a digital twin system, realizes the real-time sensing, analysis and control of a processing object along with the processing process, and forms a real-time data acquisition and analysis system; meanwhile, the sensing of the processing state variation is realized by analyzing the data in the processing process in real time, and the decision and control precision of the system in the processing process is improved, so that the precision and the efficiency of the mechanical processing system in the industrial operation process are improved.
Drawings
FIG. 1 is a schematic flow structure diagram of a digital twin system co-evolution method based on an incremental model according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
Example 1:
please refer to fig. 1; a digital twin system coevolution method based on an incremental model specifically comprises the following steps:
s1, generating digital twin data in the machining process by means of data interaction between the twin model and the physical entity based on a known digital twin system;
s2, collecting and analyzing various state variable quantities in the machining process, and acquiring data related to a decision model in the digital twin system;
s3, the digital twin system is assisted to make a decision by combining an intelligent algorithm according to the historical data of the state variation in the S2;
and S4, in the processing process, historical data of the same scene is transmitted to the digital twin system through the cloud platform, and the co-evolution of the digital twin system is promoted.
The digital twin system mentioned in S1-S4 comprises a digital twin process design unit, a processing monitoring unit and a processing quality inspection unit, wherein corresponding databases are constructed through data accumulation in the working process of the digital twin process design unit, the processing monitoring unit and the processing quality inspection unit.
And (4) marking the sample off line to update the classification model as the processing cases are accumulated, and putting the updated model into online use again.
The method comprises the following steps of cooperatively updating the model in a cooperative evolution process:
a1, defining important parameters in the updating mode, including a sharing parameter thetasTask specific parameter θ for each old taskoTraining data and truth X for new tasksnAnd Yn。
A2, model initialization, comprising: computing the output Y of an old task for new datao←CNN(Xn，θs，θo) (ii) a Randomly initializing a new parameter thetan←RANDINIT(|θn|)；
A3, model training, including defining old task output as
Define new task output as
The objective function is:
the invention is based on the self-adaptive evolution function of a digital twin system, realizes the real-time sensing, analysis and control of a processing object along with the processing process, and forms a real-time data acquisition and analysis system; meanwhile, the sensing of the processing state variation is realized by analyzing the data in the processing process in real time, and the decision and control precision of the system in the processing process is improved, so that the precision and the efficiency of the mechanical processing system in the industrial operation process are improved.
Example 2:
referring to fig. 1, based on embodiment 1 but with the difference that,
the invention provides a digital twin system, which comprises: the device comprises a digital twinning process design unit, a processing monitoring unit and a processing quality inspection unit, which belong to the production in the processing process; the system units can build a new knowledge base through continuous data accumulation to improve themselves; it includes thinking, decision-making, execution and improvement; the system realizes perception, understanding and optimization of the whole process through the accumulation of the data of the processing process along with the processing process, and achieves the process of continuously improving the data performance.
The digital twinning system generates digital twinning data in the machining process by means of data interaction between a twinning model and a physical entity, so that various state variable quantities in the cutting process are collected and analyzed to obtain data related to a decision model in the system.
In the coevolution process, the decision performance of the digital twin system is continuously improved through the historical data of the system state change sensed in the machining process and an intelligent algorithm; meanwhile, the processing process needs to be promoted along with the progress of the processing process, namely the processing process needs corresponding data support, and historical data of the same scene transmitted through a cloud platform can be applied to co-evolution.
The object which can be set up by the digital twin coevolution method is mainly in the machining field, but other fields such as assembly and workshop management can also be referred to and used.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (4)
1. A digital twin system coevolution method based on an incremental model is characterized by comprising the following steps:
s1, generating digital twin data in the machining process by means of data interaction between the twin model and the physical entity based on a known digital twin system;
s2, collecting and analyzing various state variable quantities in the machining process, and acquiring data related to a decision model in the digital twin system;
s3, the digital twin system is assisted to make a decision by combining an intelligent algorithm according to the historical data of the state variation in the S2;
and S4, in the processing process, historical data of the same scene is transmitted to the digital twin system through the cloud platform, and the co-evolution of the digital twin system is promoted.
2. The incremental model-based digital twin system coevolution method according to claim 1, wherein: the digital twin system mentioned in S1-S4 comprises a digital twin process design unit, a processing monitoring unit and a processing quality inspection unit, wherein corresponding databases are constructed through data accumulation in the working process of the digital twin process design unit, the processing monitoring unit and the processing quality inspection unit.
3. The incremental model-based digital twin system coevolution method according to claim 1, wherein: and (4) marking the sample off line to update the classification model as the processing cases are accumulated, and putting the updated model into online use again.
4. The incremental model-based digital twin system coevolution method according to claim 3, wherein the coevolution process cooperatively updates the model by the steps of:
a1, defining important parameters in the updating mode, including a sharing parameter thetasTask specific parameter θ for each old taskoTraining data and truth X for new tasksnAnd Yn，
A2, model initialization, comprising: computing the output Y of an old task for new datao←CNN(Xn，θs，θo) (ii) a Randomly initializing a new parameter thetan←RANDINIT(|θn|)；
A3, model training, including defining old task output as
Define new task output as
The objective function is:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110883308.5A CN113609672B (en) | 2021-08-03 | 2021-08-03 | Digital twin system co-evolution method based on incremental model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110883308.5A CN113609672B (en) | 2021-08-03 | 2021-08-03 | Digital twin system co-evolution method based on incremental model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113609672A true CN113609672A (en) | 2021-11-05 |
| CN113609672B CN113609672B (en) | 2024-02-02 |
Family
ID=78339102
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110883308.5A Active CN113609672B (en) | 2021-08-03 | 2021-08-03 | Digital twin system co-evolution method based on incremental model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113609672B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114706338A (en) * | 2022-04-20 | 2022-07-05 | 北京金石视觉数字科技有限公司 | Interaction control method and system based on digital twin model |
| CN117608241A (en) * | 2024-01-24 | 2024-02-27 | 山东建筑大学 | Method, system, device and medium for updating digital twin model of numerical control machine tool |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109819233A (en) * | 2019-01-21 | 2019-05-28 | 哈工大机器人（合肥）国际创新研究院 | A kind of digital twinned system based on virtual image technology |
| CN110488629A (en) * | 2019-07-02 | 2019-11-22 | 北京航空航天大学 | A kind of management-control method of the hybrid vehicle based on the twin technology of number |
| CN111210359A (en) * | 2019-12-30 | 2020-05-29 | 中国矿业大学(北京) | Intelligent mine scene oriented digital twin evolution mechanism and method |
| EP3798747A1 (en) * | 2019-09-26 | 2021-03-31 | Siemens Aktiengesellschaft | Controlling a machine based on an online digital twin |
-
2021
- 2021-08-03 CN CN202110883308.5A patent/CN113609672B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109819233A (en) * | 2019-01-21 | 2019-05-28 | 哈工大机器人（合肥）国际创新研究院 | A kind of digital twinned system based on virtual image technology |
| CN110488629A (en) * | 2019-07-02 | 2019-11-22 | 北京航空航天大学 | A kind of management-control method of the hybrid vehicle based on the twin technology of number |
| EP3798747A1 (en) * | 2019-09-26 | 2021-03-31 | Siemens Aktiengesellschaft | Controlling a machine based on an online digital twin |
| CN111210359A (en) * | 2019-12-30 | 2020-05-29 | 中国矿业大学(北京) | Intelligent mine scene oriented digital twin evolution mechanism and method |
Non-Patent Citations (3)
| Title |
|---|
| SHIMIN LIU等: "Multi-scale evolution mechanism and knowledge construction of a digital twin mimic model", ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING, pages 1 - 17 * |
| 张帆;葛世荣;李闯;: "智慧矿山数字孪生技术研究综述", 煤炭科学技术, no. 07, pages 174 - 182 * |
| 王时龙;王彦凯;杨波;王四宝;: "基于层次化数字孪生的工业互联网制造新范式――雾制造", 计算机集成制造系统, no. 12, pages 94 - 104 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114706338A (en) * | 2022-04-20 | 2022-07-05 | 北京金石视觉数字科技有限公司 | Interaction control method and system based on digital twin model |
| CN114706338B (en) * | 2022-04-20 | 2023-01-31 | 北京金石视觉数字科技有限公司 | Interaction control method and system based on digital twin model |
| CN117608241A (en) * | 2024-01-24 | 2024-02-27 | 山东建筑大学 | Method, system, device and medium for updating digital twin model of numerical control machine tool |
| CN117608241B (en) * | 2024-01-24 | 2024-04-05 | 山东建筑大学 | Method, system, device and medium for updating digital twin model of numerical control machine tool |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113609672B (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113609672B (en) | Digital twin system co-evolution method based on incremental model | |
| CN108694502B (en) | Self-adaptive scheduling method for robot manufacturing unit based on XGboost algorithm | |
| CN114118673A (en) | Workshop intelligent fault diagnosis early warning method based on digital twin technology | |
| CN113805548B (en) | Machining intelligent control system, machining intelligent control method and computer readable medium | |
| WO2017088208A1 (en) | Data-difference-driven self-learning dynamic optimization method for batch process | |
| WO2017088207A1 (en) | Model-free online rolling optimization method for batch process on basis of time period variable decomposition | |
| CN111258984B (en) | Product quality end-edge-cloud collaborative forecasting method under industrial big data environment | |
| CN112149866A (en) | Intelligent manufacturing workshop anomaly prediction and control method based on edge cloud cooperation | |
| CN114418177B (en) | New product material distribution prediction method based on digital twin workshops for generating countermeasure network | |
| CN113449919A (en) | Power consumption prediction method and system based on feature and trend perception | |
| CN110674468B (en) | Quantitative analysis method for spun yarn breakage factor based on improved rough set algorithm | |
| CN112183906A (en) | Machine room environment prediction method and system based on multi-model combined model | |
| KR102586845B1 (en) | Facility management system that enables preventive maintenance using deep learning | |
| CN112858901A (en) | System and method for monitoring operation state and service life prediction of cutter in real time | |
| Chen | Production planning and control in semiconductor manufacturing: Big data analytics and industry 4.0 applications | |
| CN112184007B (en) | Workshop equipment remote diagnosis method based on digital twin | |
| CN112231966B (en) | Cooperative robot assemblability prediction system and method based on digital twinning | |
| CN109598283B (en) | Aluminum electrolysis superheat degree identification method based on semi-supervised extreme learning machine | |
| CN110659681B (en) | Time sequence data prediction system and method based on pattern recognition | |
| CN114530163A (en) | Method and system for recognizing life cycle of equipment by adopting voice based on density clustering | |
| CN112783872A (en) | Equipment optimization model construction method based on industrial big data | |
| CN112003887A (en) | Cloud-edge collaborative deep learning device for industrial internet time sequence data prediction | |
| Binshaflout et al. | Graph neural networks for traffic pattern recognition: An overview | |
| CN112508320B (en) | Automatic process stage division workflow for batch production | |
| CN117668670B (en) | Port lifting equipment fault diagnosis method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |