CN114943185B - Nondestructive acquisition method for twin data of complex equipment under extreme working conditions - Google Patents
Nondestructive acquisition method for twin data of complex equipment under extreme working conditions Download PDFInfo
- Publication number
- CN114943185B CN114943185B CN202210817986.6A CN202210817986A CN114943185B CN 114943185 B CN114943185 B CN 114943185B CN 202210817986 A CN202210817986 A CN 202210817986A CN 114943185 B CN114943185 B CN 114943185B
- Authority
- CN
- China
- Prior art keywords
- complex equipment
- data
- model
- digital twin
- unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- 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
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a nondestructive acquisition method of twin data under extreme working conditions of complex equipment, which aims at the condition that partial units of the complex equipment cannot directly acquire data, takes digital twin as a technical means, obtains an equipment mechanism model based on an equipment twin model, data perception and actual equipment in a laboratory environment, and obtains comprehensive twin data on the premise of not damaging the mechanical structure of the equipment. Obtaining a middle-level digital twin model of the complex equipment by designing a twin model iteration module under the normal working condition of the complex equipment; designing a twin model iteration module of the complex equipment under the extreme working condition to obtain a high-level digital twin model of the complex equipment; and designing a complete-working-condition operation twin data nondestructive acquisition module of the complex equipment, and obtaining complete twin data of the equipment through deep learning and mechanism derivation. The method can effectively solve the problem that partial data cannot be directly acquired under the extreme working conditions of high speed, high precision, strong vibration, large impact and the like of partial complex equipment.
Description
Technical Field
The invention belongs to the field of electric digital data processing, and particularly relates to a nondestructive acquisition method for twin data of complex equipment under extreme working conditions.
Background
The related data of the wear state of the cutter of the numerical control machine tool running at high speed cannot be directly acquired through a sensor, in addition, part of aerospace equipment needs to work under the working conditions of strong vibration, large impact and the like, and part of the parameters of the equipment cannot be directly acquired, and the like. Part of data of the complex equipment is generally obtained by analyzing historical data in combination with a mechanism at present, so that incomplete data of the equipment in operation is caused, and fault prediction and performance evaluation of the equipment are directly influenced. If the sensor is forcibly installed, firstly, mechanical design is not allowed, and secondly, the mechanical structure can be damaged when the sensor works under the extreme working condition, on the basis of the method, the digital twin technology is used as a drive, a nondestructive acquisition method of the twin data under the extreme working condition of the complex equipment is provided, and a digital twin model of the complex equipment, particularly a mechanism model in the twin model, is iteratively constructed by combining data perception and deep learning, so that the twin data under the comprehensive working condition of the equipment can be obtained through a twin mechanism when the complex equipment actually works, and the twin data can be used for subsequent equipment state monitoring, residual life evaluation, fault prediction and the like.
Disclosure of Invention
In order to solve the technical problems, the invention provides a nondestructive acquisition method of twin data under extreme working conditions of complex equipment, which aims at the condition that partial units of the complex equipment cannot directly acquire data, takes digital twin as a technical means, obtains an equipment mechanism model by equipping a twin model, data perception and actual equipment under a laboratory environment, and obtains comprehensive twin data on the premise of not damaging the mechanical structure of the equipment. The method covers the design of a twin model iteration module under the normal working condition of the complex equipment, the design of a twin model iteration module under the extreme working condition of the complex equipment and the design of a nondestructive acquisition module for the twin data of the complex equipment under the full working condition, can effectively solve the problem that part of the complex equipment cannot directly acquire the data under the extreme working conditions of high speed, high precision, strong vibration, large impact and the like, and provides comprehensive data support for equipment state monitoring, residual life assessment, fault prediction and the like to a certain extent.
In order to achieve the purpose, the invention adopts the technical scheme that:
a method for nondestructively acquiring twin data under extreme working conditions of complex equipment comprises the following steps:
step (1), designing a twin model iteration module under the normal working condition of the complex equipment: learning and training of the deep learning module are completed by perceiving the complex equipment data, and a mechanism model of the primary digital twin model is iteratively optimized to obtain a middle-level digital twin model of the complex equipment;
step (2), designing a twin model iteration module of the complicated equipment under the extreme working condition: iteratively optimizing a mechanism model of the middle-level digital twin model through the deep learning module and combining perceived complex equipment data to obtain a high-level digital twin model of the complex equipment;
step (3), designing a twin data nondestructive acquisition module for the complete working condition operation of the complex equipment: and aiming at two conditions of normal and abnormal communication when the complex equipment actually runs, combining the deep learning module and the advanced digital twin model to obtain the twin data of the complex equipment.
Further, the step (1) specifically includes:
(1.1) structurally dividing the complex equipment into A, B two units, the first case: the unit A can be provided with sensor sensing data under all working conditions, the unit B can be provided with sensor sensing data only under normal working conditions in a laboratory environment, and the step (1.2) is carried out; in the second case: the unit A and the unit B can be provided with sensor sensing data under a laboratory environment, but the unit B cannot be provided with the sensor sensing data during actual work, and the step (1.5) is carried out;
(1.2) constructing a geometric model of the complex equipment, realizing accurate mapping with a mechanical structure of the real complex equipment, designing a mechanism model according to an operation rule of the complex equipment, coding the mechanism model, attaching the mechanism model to a geometric model background, and forming a primary digital twin model of the complex equipment by the geometric model and the mechanism model and operating the primary digital twin model in an upper computer;
(1.3) in a laboratory environment, bridging an FPGA between an upper computer and complex equipment, building a first soft core and a second soft core in the FPGA for acquiring data of an A unit and a B unit of the complex equipment respectively, designing a deep learning module in FPGA hardware logic, and communicating the first soft core, the second soft core and the FPGA hardware logic through a dual-port BRAM;
(1.4) setting the complex equipment to be under a normal working condition, wherein a first soft core in the FPGA continuously acquires the data of a unit A of the complex equipment and a second soft core in the FPGA continuously acquires the data of a unit B of the complex equipment, the two soft cores continuously add timestamps to the data and then transmit the data to the deep learning module, and the deep learning module finishes training and learning of the relevance between the data of the unit A and the data of the unit B; meanwhile, the first soft core and the second soft core continuously add timestamps to data and then transmit the data to a primary digital twin model of complex equipment of the upper computer, the primary digital twin model is driven to follow the actual complex equipment to move, the primary digital twin model of the complex equipment of the upper computer is controlled to move, generated data are transmitted to the actual complex equipment through the two FPGA soft cores, whether a mechanism model in the primary digital twin model is correct or not is judged, the mechanism model is iteratively optimized by modifying parameters until the mechanism model meets requirements, and at the moment, a middle-level digital twin model of the complex equipment is obtained;
(1.5) therefore, the complex equipment is in a normal working condition, and the unit A and the unit B can be provided with sensors for sensing data in a laboratory environment, so that the step (1.2) is returned.
Further, the step (2) specifically includes:
(2.1) setting according to the step (1.1), and aiming at the first condition, obtaining a mechanism model and a deep learning module which meet the requirements of complex equipment in the upper computer according to the step (1) because the B unit cannot be provided with sensor sensing data; under an extreme working condition, continuously acquiring the data of the unit A of the complex equipment by a first soft core in the FPGA, adding a timestamp, transmitting the data to a deep learning module, continuously obtaining the data of the unit B of the complex equipment by the deep learning module through operation, and storing the data to a second soft core;
(2.2) continuously adding timestamps on the data by the first soft core and the second soft core, transmitting the data to a middle-level digital twin model of the complex equipment of the upper computer, driving the middle-level digital twin model to follow the action of the actual complex equipment, controlling the action of the middle-level digital twin model of the complex equipment of the upper computer, transmitting the generated data to the actual complex equipment through the two soft cores of the FPGA, judging whether a mechanism model in the middle-level digital twin model is correct, iteratively optimizing the mechanism model by modifying parameters until the mechanism model meets the requirements, and obtaining a high-level digital twin model of the complex equipment at the moment;
and (2.3) setting according to the step (1.1), and further optimizing the deep learning module and the advanced digital twin model according to the step (1.4) and the step (2.2) in the second case because the B unit can be provided with sensor sensing data.
Further, the step (3) specifically includes:
(3.1) through the optimized deep learning module and the advanced digital twin model, for the two conditions in the step (1.1), when the complex equipment is in actual work, the B unit can not be provided with sensor sensing data, and at the moment, when the complex equipment and the FPGA are in normal communication, the advanced digital twin model is driven together according to the acquired A unit data and the optimized deep learning module to obtain B unit data, and the actual complex equipment running state is presented on the advanced digital twin model according to the user requirements;
and (3.2) when the complex equipment and the FPGA are abnormally communicated, evolving the actual running state of the complex equipment by taking the time specified by a user as a step length according to a mechanism model in the advanced digital twin model, and obtaining the twin data of the complex equipment.
Compared with the prior art, the invention has the advantages that: compared with the traditional mode, the method aims at the mode that partial data of the complex equipment cannot be directly acquired and only can be analyzed through the historical data afterwards, the digital twin is taken as a technical means, comprehensive twin data are acquired on the premise of not damaging the mechanical structure of the equipment, the problem that partial data of the complex equipment cannot be directly acquired under the extreme working conditions of high speed, high precision, strong vibration, large impact and the like can be effectively solved, and comprehensive data support is provided for equipment state monitoring, residual life assessment, fault prediction and the like to a certain extent.
Drawings
FIG. 1 is a structural block diagram of a nondestructive acquisition method for twin data under extreme conditions of complex equipment according to the present invention;
FIG. 2 is a flow chart of a complex equipment extreme condition twin data nondestructive acquisition method of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The method takes a digital twin technology as a drive, and obtains an accurate digital twin model, particularly a mechanism model, of the complex equipment meeting the requirements through iterative interaction among three parts, namely actual complex equipment, an equipment digital twin model and data perception shown in figure 1 in a laboratory environment. Aiming at the condition that a part of complex equipment units cannot directly acquire data, the method takes digital twinning as a technical means, obtains an equipment mechanism model by equipping a twinning model, data sensing and actual equipment in a laboratory environment, and obtains comprehensive twinning data on the premise of not damaging the mechanical structure of the equipment. The method specifically comprises the following steps: designing a twin model iteration module under the normal working condition of the complex equipment, finishing learning and training of a deep learning module by sensing complex equipment data, and iteratively optimizing a mechanism model of a primary digital twin model to obtain a middle-level digital twin model of the complex equipment; designing a twin model iteration module under the extreme working condition of the complex equipment, and iteratively optimizing a mechanism model of a middle-grade digital twin model by combining the sensed complex equipment data through the deep learning module to obtain a high-grade digital twin model of the complex equipment; designing a complete-working-condition operation twin data nondestructive acquisition module of the complex equipment, and combining the deep learning module and the advanced digital twin model to obtain the twin data of the complex equipment under the two conditions of normal and abnormal communication during the actual operation of the complex equipment.
As shown in FIG. 2, the method comprises a design complex equipment normal working condition twin model iteration module 1, a design complex equipment extreme working condition twin model iteration module 2 and a design complex equipment all-working condition operation twin data nondestructive acquisition module 3.
(1) The twin model iteration module 1 for the normal working condition of the complex equipment is specifically designed as follows:
(1.1) such as numerically controlled machine tools operating at high speed, complex equipment under strong vibration/large impact conditions, etc., it can be structurally divided into A, B two units, as shown in fig. 1, the first case: the unit A can be provided with sensor sensing data under all working conditions, the unit B can be provided with sensor sensing data only under normal working conditions under the laboratory environment (for example, the part of modules of complex equipment needs to work under the working conditions of strong vibration/large impact, the working conditions belong to extreme working conditions, and the unit B is not provided with sensor sensing data), and the step (1.2) is carried out; in the second case: sensor sensing data can be installed on the unit A and the unit B in a laboratory environment (the laboratory environment can simulate normal working conditions and extreme working conditions), but the unit B cannot install the sensor sensing data in actual working, the cutter state of a numerical control machine tool can be monitored in the laboratory environment through auxiliary modes such as high-speed vision and the like, but the working environment is noisy and severe in actual working, the state cannot be acquired through the auxiliary modes or the sensor adding mode, if the cutter state is added forcibly, the mechanical structure can be damaged in the high-speed machining process, and the step (1.5) is carried out;
(1.2) as shown in figure 1, constructing a geometric model of the complex equipment, realizing accurate mapping with a mechanical structure of the real complex equipment, designing a mechanism model according to an operation rule of the complex equipment, coding the mechanism model, attaching the mechanism model to a geometric model background, forming a primary digital twin model of the complex equipment by the geometric model and the mechanism model, and operating the primary digital twin model in an upper computer;
(1.3) under a laboratory environment, as shown in fig. 1, an FPGA is bridged between an upper computer and complex equipment, two soft cores are built in the FPGA, namely a first soft core and a second soft core are respectively used for acquiring data of an A unit and a B unit of the complex equipment, a deep learning module is designed in FPGA hardware logic, and the first soft core and the second soft core are communicated with the FPGA hardware logic through a BRAdual-port M;
(1.4) setting the complex equipment to be under a normal working condition, wherein a first soft core in the FPGA continuously acquires the data of a unit A of the complex equipment and a second soft core in the FPGA continuously acquires the data of a unit B of the complex equipment, the two soft cores continuously add timestamps to the data and then transmit the data to the deep learning module, and the deep learning module finishes training and learning of the relevance between the data of the unit A and the data of the unit B; meanwhile, the first soft core and the second soft core continuously add timestamps to data and then transmit the data to a primary digital twin model of complex equipment of an upper computer, the primary digital twin model is driven to follow the action of the actual complex equipment, in addition, a designer controls the action of the primary digital twin model of the complex equipment of the upper computer and transmits generated data to the actual complex equipment through the two FPGA soft cores, the designer judges whether a mechanism model in the digital twin model is correct according to historical experience and design rules, and iteratively optimizes the mechanism model by modifying parameters until the mechanism model meets requirements, and then a middle-level digital twin model of the complex equipment is obtained;
(1.5) therefore, the complex equipment is in a normal working condition, and A, B units can be provided with sensors to sense data in a laboratory environment, so that the step (1.2) is returned;
(2) the twin model iteration module 2 for the extreme working condition of the complex equipment is specifically designed as follows:
(2.1) setting in the same step (1.1), aiming at the first condition, because the unit B is under an extreme working condition, sensor sensing data cannot be installed, and obtaining a mechanism model and a deep learning module which meet requirements and are complex equipment in the upper computer according to the step (1); under an extreme working condition, continuously acquiring the data of the unit A of the complex equipment by a first soft core in the FPGA, adding a timestamp, transmitting the data to a deep learning module, continuously obtaining the data of the unit B of the complex equipment by the deep learning module through operation, and storing the data to a second soft core;
(2.2) the first soft core and the second soft core continuously add timestamps to data and then transmit the data to a middle-level digital twin model of the complex equipment of the upper computer, the middle-level digital twin model is driven to follow the action of the actual complex equipment, in addition, a designer controls the action of the middle-level digital twin model of the complex equipment of the upper computer and transmits the generated data to the actual complex equipment through two soft cores of the FPGA, the designer judges whether a mechanism model in the digital twin model is correct according to historical experience and design rules and iteratively optimizes the mechanism model by modifying parameters until the mechanism model meets requirements, and at this time, the high-level digital twin model of the complex equipment is obtained;
(2.3) setting in the same step (1.1), and aiming at the second situation, as the B unit is in a laboratory environment, sensor sensing data can be installed, and at the moment, in the same step (1.4) and step (2.2), a deep learning module and an advanced digital twin model are further optimized;
(3) the complex equipment full-working-condition operation twin data nondestructive acquisition module 3 is specifically designed as follows:
and (3.1) through the optimized deep learning module and the advanced digital twin model, for the two cases in the step (1.1), when the complex equipment is in actual work, the B unit cannot be provided with sensor sensing data. When the complex equipment and the FPGA are in normal communication, the advanced digital twin model is driven together according to the acquired A unit data and the optimized deep learning module to obtain B unit data, and the actual running state of the complex equipment is presented on the advanced digital twin model according to the requirements of users;
and (3.2) when the communication between the complex equipment and the FPGA is abnormal, evolving the actual running state of the complex equipment by taking the time specified by a user as a step length according to a mechanism model in the high-level digital twin model, and obtaining the twin data of the complex equipment.
In conclusion, the invention discloses a nondestructive acquisition method of twin data under extreme working conditions of complex equipment, which aims at the condition that partial units of the complex equipment cannot directly acquire data, takes digital twin as a technical means, obtains an equipment mechanism model by equipping a twin model, data perception and actual equipment under a laboratory environment, and obtains comprehensive twin data on the premise of not damaging the mechanical structure of the equipment. The problem that partial data of part of complex equipment cannot be directly acquired under extreme working conditions such as high speed, high precision, strong vibration and large impact can be effectively solved, and comprehensive data support is provided for equipment state monitoring, residual life assessment, fault prediction and the like to a certain extent.
Those skilled in the art will appreciate that the invention may be practiced without these specific details.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (3)
1. A twin data nondestructive acquisition method under extreme working conditions of complex equipment is characterized by comprising the following steps:
step (1), designing a twin model iteration module under the normal working condition of the complex equipment: learning and training of a deep learning module are completed by perceiving complex equipment data, and a mechanism model of a primary digital twin model is iteratively optimized to obtain a middle-level digital twin model of the complex equipment, wherein the method specifically comprises the following steps:
(1.1) structurally dividing the complex equipment into A, B two units, the first case: the unit A can be provided with sensor sensing data under all working conditions, the unit B can be provided with sensor sensing data only under normal working conditions in a laboratory environment, and the step (1.2) is carried out; in the second case: the unit A and the unit B can be provided with sensor sensing data under a laboratory environment, but the unit B cannot be provided with the sensor sensing data during actual work, and the step (1.5) is carried out;
(1.2) constructing a geometric model of the complex equipment, realizing accurate mapping with a mechanical structure of the real complex equipment, designing a mechanism model according to an operation rule of the complex equipment, coding the mechanism model and attaching the mechanism model to a geometric model background, wherein the geometric model and the mechanism model form a primary digital twin model of the complex equipment and operate in an upper computer;
(1.3) in a laboratory environment, bridging an FPGA between an upper computer and complex equipment, building a first soft core and a second soft core in the FPGA for acquiring data of an A unit and a B unit of the complex equipment respectively, designing a deep learning module in FPGA hardware logic, and communicating the first soft core, the second soft core and the FPGA hardware logic through a dual-port BRAM;
(1.4) setting the complex equipment to be under a normal working condition, wherein a first soft core in the FPGA continuously acquires the data of a unit A of the complex equipment and a second soft core in the FPGA continuously acquires the data of a unit B of the complex equipment, the two soft cores continuously add timestamps to the data and then transmit the data to the deep learning module, and the deep learning module finishes training and learning of the relevance between the data of the unit A and the data of the unit B; meanwhile, the first soft core and the second soft core continuously add timestamps to data and then transmit the data to a primary digital twin model of complex equipment of the upper computer, the primary digital twin model is driven to follow the actual complex equipment to move, the primary digital twin model of the complex equipment of the upper computer is controlled to move, the generated data is transmitted to the actual complex equipment through the two soft cores of the FPGA, whether a mechanism model in the primary digital twin model is correct or not is judged, the mechanism model is iteratively optimized by modifying parameters until the mechanism model meets requirements, and at the moment, a middle-level digital twin model of the complex equipment is obtained;
(1.5) when the complex equipment is in a normal working condition, and the unit A and the unit B can be provided with sensors for sensing data in a laboratory environment, so that the step (1.2) is returned;
step (2), designing a twin model iteration module under the extreme working condition of the complex equipment: iteratively optimizing a mechanism model of the intermediate digital twin model through the deep learning module and combining with the sensed complex equipment data to obtain an advanced digital twin model of the complex equipment;
step (3), designing a complex equipment full-working-condition operation twin data nondestructive acquisition module: and aiming at two conditions of normal and abnormal communication when the complex equipment is actually operated, combining the deep learning module and the advanced digital twin model to obtain the twin data of the complex equipment.
2. The method for non-destructively acquiring the twin data under the extreme working condition of the complex equipment as recited in claim 1, wherein the step (2) specifically comprises:
(2.1) setting according to the step (1.1), and aiming at the first condition, sensor sensing data cannot be installed due to the fact that the unit B is in an extreme working condition, and obtaining a mechanism model and a deep learning module which meet requirements of complex equipment in the upper computer according to the step (1); under an extreme working condition, continuously acquiring the data of the unit A of the complex equipment by a first soft core in the FPGA, adding a timestamp, transmitting the data to a deep learning module, continuously obtaining the data of the unit B of the complex equipment by the deep learning module through operation, and storing the data to a second soft core;
(2.2) continuously adding timestamps on the data by the first soft core and the second soft core, transmitting the data to a middle-level digital twin model of the complex equipment of the upper computer, driving the middle-level digital twin model to follow the action of the actual complex equipment, controlling the action of the middle-level digital twin model of the complex equipment of the upper computer, transmitting the generated data to the actual complex equipment through the two soft cores of the FPGA, judging whether a mechanism model in the middle-level digital twin model is correct, iteratively optimizing the mechanism model by modifying parameters until the mechanism model meets the requirements, and obtaining a high-level digital twin model of the complex equipment at the moment;
(2.3) setting according to step (1.1), for the second case, because the B unit can install sensor perception data in the laboratory environment, then according to step (1.4) and step (2.2), further optimizing the deep learning module and the advanced digital twin model.
3. The method for nondestructively acquiring twin data in extreme conditions of complex equipment as claimed in claim 2, wherein said step (3) specifically comprises:
(3.1) through the optimized deep learning module and the advanced digital twin model, for the two conditions in the step (1.1), when the complex equipment is in actual work, the B unit can not be provided with sensor sensing data, and at the moment, when the complex equipment and the FPGA are in normal communication, the advanced digital twin model is driven together according to the acquired A unit data and the optimized deep learning module to obtain B unit data, and the actual complex equipment running state is presented on the advanced digital twin model according to the user requirements;
and (3.2) when the communication between the complex equipment and the FPGA is abnormal, evolving the actual running state of the complex equipment by taking the time specified by a user as a step length according to a mechanism model in the high-level digital twin model, and obtaining the twin data of the complex equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210817986.6A CN114943185B (en) | 2022-07-13 | 2022-07-13 | Nondestructive acquisition method for twin data of complex equipment under extreme working conditions |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210817986.6A CN114943185B (en) | 2022-07-13 | 2022-07-13 | Nondestructive acquisition method for twin data of complex equipment under extreme working conditions |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114943185A CN114943185A (en) | 2022-08-26 |
| CN114943185B true CN114943185B (en) | 2022-09-30 |
Family
ID=82910188
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210817986.6A Active CN114943185B (en) | 2022-07-13 | 2022-07-13 | Nondestructive acquisition method for twin data of complex equipment under extreme working conditions |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114943185B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111008502A (en) * | 2019-11-25 | 2020-04-14 | 北京航空航天大学 | Fault prediction method for complex equipment driven by digital twin |
| CN113126569A (en) * | 2021-04-19 | 2021-07-16 | 北京航空航天大学 | Digital twin equipment construction method and system |
| CN113743019A (en) * | 2021-09-16 | 2021-12-03 | 北京航空航天大学 | Digital twin enhanced complex equipment health monitoring method |
| CN114638160A (en) * | 2022-05-11 | 2022-06-17 | 西南交通大学 | Knowledge service method for complex equipment digital twin model |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112417619B (en) * | 2020-11-23 | 2021-10-08 | 江苏大学 | Pump unit optimal operation adjusting system and method based on digital twinning |
-
2022
- 2022-07-13 CN CN202210817986.6A patent/CN114943185B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111008502A (en) * | 2019-11-25 | 2020-04-14 | 北京航空航天大学 | Fault prediction method for complex equipment driven by digital twin |
| CN113126569A (en) * | 2021-04-19 | 2021-07-16 | 北京航空航天大学 | Digital twin equipment construction method and system |
| CN113743019A (en) * | 2021-09-16 | 2021-12-03 | 北京航空航天大学 | Digital twin enhanced complex equipment health monitoring method |
| CN114638160A (en) * | 2022-05-11 | 2022-06-17 | 西南交通大学 | Knowledge service method for complex equipment digital twin model |
Non-Patent Citations (1)
| Title |
|---|
| 数据驱动的复杂产品智能服务技术与应用;李浩等;《中国机械工程》;20200410;第31卷(第07期);第0节,第3.3节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114943185A (en) | 2022-08-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110704974B (en) | Modeling and using method of process model based on digital twin driving | |
| US11897068B2 (en) | Information processing method, information processing system, and information processing device | |
| TWI640390B (en) | Tool wear monitoring and predicting method | |
| CN107111297B (en) | Computer-implemented method for the analysis of a part of a workpiece machined by at least one computer-numerically-controlled machine | |
| JP6031202B1 (en) | Cell control device for finding the cause of abnormalities in manufacturing machines | |
| Zhu et al. | A cyber-physical production system framework of smart CNC machining monitoring system | |
| CN102929210B (en) | Control and optimization system for feature-based numerical control machining process and control and optimization method therefor | |
| JP5997330B1 (en) | Machine learning apparatus capable of determining whether or not spindle replacement is required, spindle replacement determination apparatus, control apparatus, machine tool and production system, and machine learning method | |
| CN102073300B (en) | Tool wear monitoring system capable of realizing self-learning in numerical control machining state | |
| US20200279158A1 (en) | Machining condition adjustment device and machining condition adjustment system | |
| EP2916187B1 (en) | Improved database for chatter predictions | |
| CN113722979B (en) | Digital twinning-based virtual-real interaction system of coal mining machine and construction method thereof | |
| CN110605709B (en) | Digital twin and precise filtering drive robot integration system and use method thereof | |
| JP6333868B2 (en) | Cell control device and production system for managing the operating status of a plurality of manufacturing machines in a manufacturing cell | |
| CN101334656A (en) | Numerical control machine processability monitoring system | |
| Tan et al. | Distributed fault detection in industrial system based on sensor wireless network | |
| WO2003079123A1 (en) | Intelligent step-nc controller | |
| CN102848266B (en) | Machine tool spindle accuracy prediction method | |
| JP2010146537A (en) | Machining support monitoring method turned artificially intelligent, and machining support monitoring system turned artificially intelligent | |
| KR20190043038A (en) | Signal Processing Method For Adaptive Vibration Control Of Machine Tools | |
| JP2019220164A (en) | Smart adjustment system and its method | |
| CN114943185B (en) | Nondestructive acquisition method for twin data of complex equipment under extreme working conditions | |
| CN109799787B (en) | Intelligent camshaft grinding process software database system based on numerical control system | |
| CN110647108A (en) | Data-driven numerical control turning element action energy consumption prediction method | |
| CN117170310A (en) | Digital twin-based remote fault diagnosis method and system for numerical control machine tool |
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 |