CN116880372A - Operation optimization method and system of digital twin plant - Google Patents
Operation optimization method and system of digital twin plant Download PDFInfo
- Publication number
- CN116880372A CN116880372A CN202310705574.8A CN202310705574A CN116880372A CN 116880372 A CN116880372 A CN 116880372A CN 202310705574 A CN202310705574 A CN 202310705574A CN 116880372 A CN116880372 A CN 116880372A
- Authority
- CN
- China
- Prior art keywords
- data
- real
- time
- factory
- production
- 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
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000005457 optimization Methods 0.000 title claims abstract description 14
- 238000004519 manufacturing process Methods 0.000 claims abstract description 199
- 238000004458 analytical method Methods 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000005516 engineering process Methods 0.000 claims abstract description 17
- 238000012800 visualization Methods 0.000 claims abstract description 8
- 230000002159 abnormal effect Effects 0.000 claims description 40
- 238000010276 construction Methods 0.000 claims description 32
- 238000005286 illumination Methods 0.000 claims description 16
- 238000005265 energy consumption Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 14
- 238000012795 verification Methods 0.000 claims description 12
- 238000007726 management method Methods 0.000 claims description 11
- 238000013507 mapping Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000013523 data management Methods 0.000 abstract description 6
- 230000000694 effects Effects 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 6
- 238000013461 design Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000005094 computer simulation Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000011960 computer-aided design Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
- G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32252—Scheduling production, machining, job shop
Abstract
The application relates to the technical field of digital factories and provides an operation optimization method and an operation optimization system of a digital twin factory. The method comprises the following steps: collecting factory base data by a plurality of sensors; performing real-time comprehensive analysis on a plurality of data of a production line based on the factory basic data; constructing a digital twin model based on a 3D visualization technology; inputting the N production line comprehensive data into the digital twin model, and outputting N real-time running state information; obtaining the predicted production state of the target factory according to the N pieces of real-time running state information; and performing overlay traversal on the real-time production state based on the predicted production state, and processing the real-time production state of the target factory. The application solves the problem of errors caused by hysteresis and manual collection of the traditional factory data management, and achieves the technical effects of improving the accuracy and timeliness of factory data processing and avoiding delay production.
Description
Technical Field
The application relates to the technical field of digital factories, in particular to an operation optimization method and an operation optimization system of a digital twin factory.
Background
The digital factory is a novel production organization mode which simulates, evaluates and optimizes the whole production process in a computer virtual environment and further expands the whole product life cycle, and is a product of combining a modern digital manufacturing technology and a computer simulation technology. As one of key technologies of digital and intelligent manufacturing, a digital factory is an application embodiment of modern industrialization and informatization integration, and is a necessary way for realizing intelligent manufacturing. The digital factory can provide an integral solution for comprehensively controlling the whole production process of the manufacturing factory by means of integration, simulation, analysis, control and the like by means of informatization and digitalization technologies.
Digital factories are dynamic information feedback of process states of a factory lifecycle, including production, operation, modification, maintenance, and disablement. The dynamic digital factory database system is continuously input by different departments of the initial operation information of production in factory projects, the stable or abnormal information in the production operation process, the final data before scrapping and the like. The digital factory provides accurate data through long-term comprehensive collection, and can provide basis for management decision-making processes such as fault diagnosis and analysis.
In summary, the application solves the problems of hysteresis and errors caused by manual collection of the traditional factory data management.
Disclosure of Invention
Based on the above, it is necessary to provide a method and a system for optimizing operation of a digital twin plant capable of improving accuracy and timeliness of plant data processing and avoiding delay production, so as to solve the technical problems of hysteresis of traditional plant data management and errors caused by manual collection in the prior art, thereby improving accuracy and timeliness of plant data processing and avoiding delay production.
In a first aspect, an embodiment of the present application provides a method for optimizing operation of a digital twin plant, the method comprising: collecting factory base data by a plurality of sensors; real-time comprehensive analysis is carried out on a plurality of data of the production lines based on the factory basic data, N production line comprehensive data are determined, and N is a positive integer greater than or equal to 2; constructing a digital twin model based on a 3D visualization technology; inputting the N production line comprehensive data into the digital twin model, and outputting N real-time running state information; obtaining the predicted production state of the target factory according to the N pieces of real-time running state information; and performing overlay traversal on the real-time production state based on the predicted production state, and processing the real-time production state of the target factory according to an abnormal traversal result.
In a second aspect, an embodiment of the present application further provides an operation optimization system of a digital twin plant, wherein the system includes: the factory basic data acquisition module is used for acquiring factory basic data through a plurality of sensors; the production line comprehensive data determining module is used for carrying out real-time comprehensive analysis on a plurality of data of the production line based on the factory basic data to determine N production line comprehensive data, wherein N is a positive integer greater than or equal to 2; the digital twin module construction module is used for constructing a digital twin model based on a 3D visualization technology; the real-time running state information output module is used for inputting the N production line comprehensive data into the digital twin model and outputting N real-time running state information; the predicted production obtaining module is used for obtaining predicted production states of the target factory according to the N pieces of real-time running state information; and the real-time production state processing module is used for performing coverage traversal on the real-time production state based on the predicted production state and processing the real-time production state of the target factory according to an abnormal traversal result.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
firstly, collecting factory basic data through a plurality of sensors; then, carrying out real-time comprehensive analysis on a plurality of data of the production line based on the factory basic data to determine N production line comprehensive data, wherein N is a positive integer greater than or equal to 2; constructing a digital twin model based on a 3D visualization technology; inputting the N production line comprehensive data into the digital twin model, and outputting N pieces of real-time running state information; then, according to the N pieces of real-time running state information, obtaining the predicted production state of the target factory; and finally, performing coverage traversal on the real-time production state based on the predicted production state, and processing the real-time production state of the target factory according to an abnormal traversal result. The application solves the technical problems of hysteresis of traditional factory data management and errors caused by manual collection in the prior art by providing the operation optimization method and the system of the digital twin factory, and achieves the technical effects of improving the accuracy and timeliness of factory data processing and avoiding delay production.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
FIG. 1 is a flow diagram of a method of optimizing operation of a digital twin plant in one embodiment;
FIG. 2 is a schematic diagram of the basic data flow of the plant for constructing an operation optimization method of the digital twin plant in one embodiment;
FIG. 3 is a block diagram of an operational optimization system of a digital twin plant in one embodiment.
Reference numerals illustrate: the system comprises a factory basic data acquisition module 11, a production line comprehensive data determination module 12, a digital twin module construction module 13, a real-time running state information output module 14, a predicted production acquisition module 15 and a real-time production state processing module 16.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
Having introduced the basic principles of the present application, the technical solutions of the present application will now be clearly and fully described with reference to the accompanying drawings, it being apparent that the embodiments described are only some, but not all, embodiments of the present application, and it is to be understood that the present application is not limited to the exemplary embodiments described herein. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application. It should be further noted that, for convenience of description, only some, but not all of the drawings related to the present application are shown.
Example 1
As shown in fig. 1, the present application provides a method of optimizing operation of a digital twin plant, the method comprising:
s100: collecting factory base data by a plurality of sensors;
specifically, the digital factory is a novel production organization mode for simulating, evaluating and optimizing the whole production process in a computer virtual environment and further expanding the whole product life cycle. The product is a combination of the modern digital manufacturing technology and the computer simulation technology, and is mainly used as a bridge for communicating product design and product manufacturing; because the digital factory is essentially integrated with information, basic data of the factory is acquired through a plurality of sensors, wherein the sensors comprise a humidity sensor, a temperature sensor and a photosensitive sensor, and the basic data refer to humidity data, temperature data and illumination data of a target factory; by collecting basic data of the factory, the virtual factory can be engraved in an equal ratio to the real production environment 1:1, and provides data support for the construction of the digital twin factories.
As shown in fig. 2, further, the steps of the present application include:
s110: extracting historical humidity data, historical temperature data and historical illumination data of a target factory in the humidity sensor through the humidity sensor, the temperature sensor and the photosensitive sensor;
s120: acquiring operation parameters of M devices in the target factory based on the historical humidity data, the historical temperature data and the historical illumination data, wherein M is a positive integer;
s130: acquiring capacity data of key positions in a production line based on production efficiency, wherein the capacity data and operation parameters of the M devices are in a corresponding relation;
s140: and constructing the factory basic data according to the operation parameters of the M devices and the productivity data.
Specifically, firstly, historical humidity data, historical temperature data and historical illumination data of a target factory in the humidity sensor are extracted through the humidity sensor, the temperature sensor and the photosensitive sensor; acquiring operation parameters of M devices in the target plant based on the historical humidity data, the historical temperature data and the historical illumination data, wherein the operation parameters of the devices comprise various operation configurations of the devices, such as device operation states, device operation time parameters, device operation speed parameters, device operation pressure parameters and the like, and the optimal humidity data, the optimal temperature data and the illumination intensity required by the operation of the M devices in the target plant can be acquired to influence the production process, and M is a positive integer; based on production efficiency, which means the ratio between the actual output and the maximum output of a process under the condition of fixed input, acquiring yield data of key positions in a production line, wherein the yield data refers to yield of good products in unit working time, the yield data and the operating parameters of M devices are in corresponding relation, the influence of the basic data on the operating parameters is acquired by extracting historical humidity data, historical temperature data and historical illumination data, and then the influence of the operating parameters on the yield data is acquired, for example, the product of a certain production line is invisible light, and at the moment, the smaller the illumination data is, the more yield of good products in unit working time is; and constructing the factory basic data according to the operation parameters of the M devices and the productivity data. Support is provided for the subsequent construction of the digital twin plant.
S200: real-time comprehensive analysis is carried out on a plurality of data of the production lines based on the factory basic data, N production line comprehensive data are determined, and N is a positive integer greater than or equal to 2;
specifically, a plurality of data of a production line are comprehensively analyzed in real time based on the factory basic data, wherein the production line refers to a route through which a product production process passes, and mainly refers to synchronous comprehensive analysis of data generated in a production operation process, such as operation data of equipment, production execution data of the production line, factory stacking, production, transportation data and the like, according to the factory basic data, and the comprehensive analysis refers to operation analysis of real-time factory stacking of the production line based on equipment operation parameters in a factory to obtain stacking operation data; analyzing the real-time output of the production line according to the productivity data in the production line to obtain output data, and analyzing the real-time transportation frequency of the production line according to the output data to obtain transportation frequency data; and finally, adding the stacking operation data, the output data and the transportation frequency data into the production line comprehensive data. And determining comprehensive data of N production lines, wherein N is a positive integer greater than or equal to 2, and mainly aims to monitor the operation condition of the production process.
Further, the steps of the application also comprise:
s241: performing operation analysis on the real-time factory stacking of the production line based on the operation parameters of the M devices to obtain stacking operation data;
s242: carrying out real-time output analysis of the production line on the production line based on the productivity data to obtain output data;
s243: analyzing the real-time transportation frequency of the production line according to the output data to obtain transportation frequency data;
s244: and adding the stacker operation data, the output data and the transportation frequency data into the N production line comprehensive data.
Specifically, performing operation analysis on real-time factory stacking of the production line based on the operation parameters of the M devices to obtain stacking operation data, wherein the factory stacking refers to initial materials; carrying out real-time output analysis of the production line on the production line based on the productivity data to obtain output data, and carrying out real-time transportation frequency analysis of the production line according to the output data to obtain transportation frequency data; by analyzing the real-time factory stacking transportation and the real-time output, the real-time factory stacking is divided by the real-time output, the real-time transportation frequency of the production line is equal to the real-time transportation frequency of the production line, the transportation frequency data is obtained, the real-time transportation frequency in the middle refers to the transportation frequency synchronized when the factory is operating, for example, the transportation frequency of the production line is thousands of times a day at a time point, the transportation frequency data of the production line can be obtained, and the stacking operation data, the output data and the transportation frequency data are added into the comprehensive data of the N production lines, so that data support is provided for constructing a digital twin model later.
S300: constructing a digital twin model based on a 3D visualization technology;
specifically, with the progress and popularization of virtual reality technology, people except the game industry pay attention to the fact that 3D virtual visual reality technology is used in industrial industries such as many parks, buildings, fire protection and the like, and a digital twin model is built through the 3D visual technology, wherein the digital twin model refers to a model capable of presenting real-time running conditions of a factory.
Further, the method comprises the following steps:
s310: acquiring a plurality of real-time sensing data in the target factory through the plurality of sensors;
s320: constructing 3D models of M devices in the target factory through a CAD model;
s330: based on the 3D models of the M devices, adjusting the plurality of real-time sensing data to obtain a plurality of real-time sensing adjustment data;
s340: taking the 3D models of the M devices and the plurality of real-time sensing adjustment data as a first construction data set;
s350: the digital twin model is constructed based on the first construction data.
Specifically, real-time humidity data, real-time temperature data and real-time illumination data in the target factory are obtained through a humidity sensor, a temperature sensor and a photosensitive sensor in the target factory; and constructing a 3D model of M devices in the target factory through a CAD model, wherein CAD is abbreviated as computer aided design (ComputerAidDesign), and the CAD is used for helping a designer to perform design work by utilizing a computer and graphic devices thereof. The designer usually starts the design by using a sketch, and the heavy work of changing the sketch into a working drawing can be finished by a computer, so that the drawing software can be used for constructing a 3D model of M devices in a factory; adjusting the plurality of real-time sensing data based on the 3D models of the M devices to obtain a plurality of real-time sensing adjustment data, and adjusting the real-time humidity data, the real-time temperature data and the real-time illumination data in the target factory based on the 3D models of the M devices to obtain a plurality of real-time sensing adjustment data; taking the 3D models of the M devices and the plurality of real-time sensing adjustment data as a first construction data set; the digital twin model is constructed based on the first construction data.
Further, the steps of the application also comprise:
s351: the digital twin model comprises a data input layer, an operation state acquisition layer and a state result output layer;
s352: performing data annotation on the 3D models of the M devices and the plurality of real-time sensing adjustment data to obtain a first construction data set, wherein the first construction data set comprises a first training set and a first verification set;
s353: and performing supervision training and verification on the digital twin model by adopting the first training set and the first verification set until the digital twin model converges or the accuracy reaches a preset requirement, and completing the construction of the digital twin model.
The method comprises the steps of specifically, constructing a digital twin model, wherein the digital twin model comprises a data input layer, an operation state acquisition layer and a state result output layer, wherein a first construction data set is obtained by carrying out data annotation on a 3D model of M devices and the real-time sensing adjustment data, and the first construction data set comprises a first training set and a first verification set; inputting a plurality of sample data in a first training set into a digital twin model, and performing supervised training on the digital twin model by using sample parameters in the first verification set to enable the digital twin model to be consistent with the actual condition of the target factory; after the data in the first training set is trained, a trained digital twin model can be obtained, in short, the error between the actual model and the construction is taken as a loss function, the smaller the loss function is, the smaller the error is, and the digital twin model with the accuracy meeting the preset condition can be obtained. By constructing the digital twin model, the accuracy of the model is trained, the simulation accuracy of the digital twin model is improved, and the method achieves the following steps of 1:1 corresponds to the technical effect of the reduced digital twin model.
S400: inputting the N production line comprehensive data into the digital twin model, and outputting N real-time running state information;
s500: obtaining the predicted production state of the target factory according to the N pieces of real-time running state information;
specifically, N pieces of real-time operation state information can be output by integrating the N production line integrated data, that is, the stacker operation data, the yield data, and the transportation frequency data of the production line, into the digital twin model. And obtaining the predicted production state of the target factory according to the N pieces of real-time running state information, namely the real-time humidity data, the real-time temperature data and the real-time illumination data in the target factory.
Further, the method comprises the following steps:
s510: trend prediction is carried out on the N pieces of real-time running state information through a time sequence prediction algorithm, and running trend information is obtained;
s520: defining a production time sequence, and obtaining a mapping relation between the production time sequence and the running trend information;
specifically, the time series prediction predicts the future by using historical data and the correlation between the historical humidity data, the historical temperature data, the historical illumination data, the stacker operation data, the output data and the transportation frequency data of the target factory and time, and the N pieces of real-time operation state information are subjected to trend prediction by using a time series prediction algorithm to obtain the real-time operation prediction state of the target factory, wherein the production time series is defined in time sequence according to time nodes corresponding to the production flow by using past time series data, such as the historical sensing data is subjected to statistical analysis, the development trend of the production is deduced, the historical data is used for statistical analysis in order to eliminate the influence caused by random fluctuation, and the data is subjected to proper processing, such as training set, verification set and test set, so that the trend prediction is performed. By defining a time sequence, which is also called a time sequence, a historical complex number or a dynamic sequence, in mathematics, the time sequence is a series of data points indexed (or listed or chart) in time sequence, and the production time sequence is defined in time sequence according to a time node corresponding to a production flow, for example, the production line needs to perform operation analysis on real-time factory piles of the production line at one point, and needs to perform rough machining on initial materials of the production line at three points; and obtaining a mapping relation between the production time sequence and the operation trend information, wherein the mapping relation is a corresponding relation from a number set to a number set, namely, what production processing should be carried out by the production line in a time node corresponding to a production flow. The application solves the problems of hysteresis and manual acquisition caused by the traditional factory data management.
S600: and performing overlay traversal on the real-time production state based on the predicted production state, and processing the real-time production state of the target factory according to an abnormal traversal result.
Specifically, based on the predicted production state, all information in the real-time production state is accessed to obtain a result that the predicted production state is different from the real-time production state, so to speak, a result that the production equipment fails, that is, an abnormal traversal result, and the real-time production state of the target plant is processed, for example, an alarm is sent out, a main control system is fed back, and the like.
Further, the method comprises the following steps:
s610: traversing the production line in real time to extract abnormal production state results;
s620: performing real-time operation state traversal on M devices in the production line, and extracting operation state abnormal results;
s630: performing real-time energy consumption traversal on M devices in the production line, and extracting an energy consumption abnormal result;
s640: generating a factory operation early warning instruction based on the production state abnormal result, the operation state abnormal result and the energy consumption abnormal result;
s650: and sending the factory operation early warning instruction to a background management system, and scheduling management personnel through the background management system.
Specifically, all information in the real-time production state of the production line is accessed, and abnormal production state results such as production quantity reduction and the like are extracted; accessing all information of real-time operation states of M devices in the production line, and extracting abnormal operation state results, such as non-operation of the production devices; accessing all information of real-time energy consumption of M devices in the production line, and extracting energy consumption abnormal results, such as abnormal electricity consumption of the production devices; generating a factory operation early warning instruction based on the production state abnormal result, the operation state abnormal result and the energy consumption abnormal result, wherein the factory operation early warning instruction is that the production factory possibly has abnormal problems and needs to be repaired in time; and sending the factory operation early warning instruction to a background management system, namely, detecting equipment or events with abnormal production, abnormal operation and excessive energy consumption, early warning the equipment or events to a background management interface in real time, and checking, verifying and processing the equipment or events remotely by a manager in time through the system. The application solves the technical problems of errors caused by hysteresis of traditional factory data management and manual acquisition by constructing a digital twin factory, and achieves the technical effects of improving the accuracy and timeliness of factory data processing and avoiding delay production.
Example two
As shown in fig. 3, the present application also provides an operation optimization system of a digital twin plant, the system comprising:
a factory basic data collection module 11, wherein the factory basic data collection module 11 is used for collecting factory basic data through a plurality of sensors;
a production line comprehensive data determining module 12, where the production line comprehensive data determining module 12 is configured to perform real-time comprehensive analysis on a plurality of data of a production line based on the factory basic data, determine N production line comprehensive data, and N is a positive integer greater than or equal to 2;
a digital twin module construction module 13, wherein the digital twin module construction module 13 is used for constructing a digital twin model based on a 3D visualization technology;
the real-time running state information output module 14, wherein the real-time running state information output module 14 is used for inputting the N production line comprehensive data to the digital twin model and outputting N real-time running state information;
a predicted production obtaining module 15, where the predicted production obtaining module 15 is configured to obtain a predicted production state of the target plant according to the N pieces of real-time running state information;
the real-time production state processing module 16 is configured to overlay the real-time production state based on the predicted production state, and process the real-time production state of the target plant according to an abnormal traversal result.
Further, the embodiment of the application further comprises:
the historical data extraction module is used for extracting historical humidity data, historical temperature data and historical illumination data of a target factory in the humidity sensor through the humidity sensor, the temperature sensor and the photosensitive sensor;
the device operation parameter acquisition module is used for acquiring operation parameters of M devices in the target factory based on the historical humidity data, the historical temperature data and the historical illumination data, wherein M is a positive integer;
the productivity data acquisition module is used for acquiring productivity data of key positions in a production line based on production efficiency, wherein the productivity data and operation parameters of the M devices are in a corresponding relation;
and the factory basic data construction module is used for constructing the factory basic data according to the operation parameters of the M devices and the productivity data.
Further, the embodiment of the application further comprises:
the stacker operation data acquisition module is used for carrying out operation analysis on the real-time factory stackers of the production line based on the operation parameters of the M devices to acquire stacker operation data;
the output data acquisition module is used for carrying out real-time output analysis of the production line on the production line based on the capacity data to acquire output data;
the transportation frequency data acquisition module is used for analyzing the real-time transportation frequency of the production line according to the output data to acquire transportation frequency data;
and the production line comprehensive data adding module is used for adding the stacking operation data, the output data and the transportation frequency data into the N production line comprehensive data.
Further, the embodiment of the application further comprises:
the real-time sensing data acquisition module is used for acquiring a plurality of real-time sensing data in the target factory through the plurality of sensors;
the device 3D model building module is used for building 3D models of M devices in the target factory through a CAD model;
the real-time sensing adjustment data acquisition module is used for adjusting the plurality of real-time sensing data based on the 3D models of the M devices to acquire a plurality of real-time sensing adjustment data;
a first construction dataset module for taking the 3D models of the M devices, the plurality of real-time sensory modulation data as a first construction dataset;
the digital twin model construction module is used for constructing the digital twin model based on the first construction data.
Further, the embodiment of the application further comprises:
the digital twin model comprises a module, wherein the digital twin model comprises a data input layer, an operation state acquisition layer and a state result output layer;
the first construction data set obtaining module is used for carrying out data labeling on the 3D models of the M devices and the real-time sensing adjustment data to obtain a first construction data set, wherein the first construction data set comprises a first training set and a first verification set;
the digital twin model construction completion module is used for performing supervision training and verification on the digital twin model by adopting the first training set and the first verification set until the digital twin model converges or the accuracy reaches a preset requirement, and then the construction of the digital twin model is completed.
Further, the embodiment of the application further comprises:
the operation trend information obtaining module is used for carrying out trend prediction on the N pieces of real-time operation state information through a time sequence prediction algorithm to obtain operation trend information;
the production time sequence definition module is used for defining a production time sequence and obtaining a mapping relation between the production time sequence and the running trend information;
and the mapping relation adding module is used for adding the mapping relation into the predicted production state of the target plant.
Further, the embodiment of the application further comprises:
the production state abnormal result extraction module is used for carrying out real-time production state traversal on the production line and extracting a production state abnormal result;
the operation abnormal state result extraction module is used for performing real-time operation state traversal on M devices in the production line and extracting operation state abnormal results;
the energy consumption abnormal result extraction module is used for performing real-time energy consumption traversal on M devices in the production line and extracting energy consumption abnormal results;
the factory operation early warning instruction generation module is used for generating a factory operation early warning instruction based on the production state abnormal result, the operation state abnormal result and the energy consumption abnormal result;
and the manager scheduling module is used for sending the factory operation early warning instruction to a background management system and scheduling the manager through the background management system.
For specific embodiments of the operation optimization system of the digital twin plant, reference may be made to the above embodiments of an operation optimization method of the digital twin plant, and a detailed description thereof will be omitted. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (8)
1. A method of optimizing the operation of a digital twin plant, the method comprising:
collecting factory base data by a plurality of sensors;
real-time comprehensive analysis is carried out on a plurality of data of the production lines based on the factory basic data, N production line comprehensive data are determined, and N is a positive integer greater than or equal to 2;
constructing a digital twin model based on a 3D visualization technology;
inputting the N production line comprehensive data into the digital twin model, and outputting N real-time running state information;
obtaining the predicted production state of the target factory according to the N pieces of real-time running state information;
and performing overlay traversal on the real-time production state based on the predicted production state, and processing the real-time production state of the target factory according to an abnormal traversal result.
2. The method of claim 1, wherein the plant base data, the method further comprising:
extracting historical humidity data, historical temperature data and historical illumination data of a target factory in the humidity sensor through the humidity sensor, the temperature sensor and the photosensitive sensor;
acquiring operation parameters of M devices in the target factory based on the historical humidity data, the historical temperature data and the historical illumination data, wherein M is a positive integer;
acquiring capacity data of key positions in a production line based on production efficiency, wherein the capacity data and operation parameters of the M devices are in a corresponding relation;
and constructing the factory basic data according to the operation parameters of the M devices and the productivity data.
3. The method of claim 2, wherein the N production line integrated data is determined, the method further comprising:
performing operation analysis on the real-time factory stacking of the production line based on the operation parameters of the M devices to obtain stacking operation data;
carrying out real-time output analysis of the production line on the production line based on the productivity data to obtain output data;
analyzing the real-time transportation frequency of the production line according to the output data to obtain transportation frequency data;
and adding the stacker operation data, the output data and the transportation frequency data into the N production line comprehensive data.
4. The method of claim 1, wherein a digital twin model is constructed, the method further comprising:
acquiring a plurality of real-time sensing data in the target factory through the plurality of sensors;
constructing 3D models of M devices in the target factory through a CAD model;
based on the 3D models of the M devices, adjusting the plurality of real-time sensing data to obtain a plurality of real-time sensing adjustment data;
taking the 3D models of the M devices and the plurality of real-time sensing adjustment data as a first construction data set;
the digital twin model is constructed based on the first construction data.
5. The method of claim 4, wherein the method further comprises:
the digital twin model comprises a data input layer, an operation state acquisition layer and a state result output layer;
performing data annotation on the 3D models of the M devices and the plurality of real-time sensing adjustment data to obtain a first construction data set, wherein the first construction data set comprises a first training set and a first verification set;
and performing supervision training and verification on the digital twin model by adopting the first training set and the first verification set until the digital twin model converges or the accuracy reaches a preset requirement, and completing the construction of the digital twin model.
6. The method of claim 1, wherein a predicted production status of the target plant is obtained, the method further comprising:
trend prediction is carried out on the N pieces of real-time running state information through a time sequence prediction algorithm, and running trend information is obtained;
defining a production time sequence, and obtaining a mapping relation between the production time sequence and the running trend information;
the mapping relationship is added to the predicted production state of the target plant.
7. The method of claim 1, wherein the real-time production status of the target plant is processed, the method further comprising:
traversing the production line in real time to extract abnormal production state results;
performing real-time operation state traversal on M devices in the production line, and extracting operation state abnormal results;
performing real-time energy consumption traversal on M devices in the production line, and extracting an energy consumption abnormal result;
generating a factory operation early warning instruction based on the production state abnormal result, the operation state abnormal result and the energy consumption abnormal result;
and sending the factory operation early warning instruction to a background management system, and scheduling management personnel through the background management system.
8. An operation optimization system of a digital twin plant, the system comprising:
the factory basic data acquisition module is used for acquiring factory basic data through a plurality of sensors;
the production line comprehensive data determining module is used for carrying out real-time comprehensive analysis on a plurality of data of the production line based on the factory basic data to determine N production line comprehensive data, wherein N is a positive integer greater than or equal to 2;
the digital twin module construction module is used for constructing a digital twin model based on a 3D visualization technology;
the real-time running state information output module is used for inputting the N production line comprehensive data into the digital twin model and outputting N real-time running state information;
the predicted production obtaining module is used for obtaining predicted production states of the target factory according to the N pieces of real-time running state information;
and the real-time production state processing module is used for performing coverage traversal on the real-time production state based on the predicted production state and processing the real-time production state of the target factory according to an abnormal traversal result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310705574.8A CN116880372A (en) | 2023-06-15 | 2023-06-15 | Operation optimization method and system of digital twin plant |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310705574.8A CN116880372A (en) | 2023-06-15 | 2023-06-15 | Operation optimization method and system of digital twin plant |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116880372A true CN116880372A (en) | 2023-10-13 |
Family
ID=88259463
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310705574.8A Pending CN116880372A (en) | 2023-06-15 | 2023-06-15 | Operation optimization method and system of digital twin plant |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116880372A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117092977A (en) * | 2023-10-19 | 2023-11-21 | 山东汇颐信息技术有限公司 | Industrial digital twin data space construction method, system, equipment and medium |
-
2023
- 2023-06-15 CN CN202310705574.8A patent/CN116880372A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117092977A (en) * | 2023-10-19 | 2023-11-21 | 山东汇颐信息技术有限公司 | Industrial digital twin data space construction method, system, equipment and medium |
| CN117092977B (en) * | 2023-10-19 | 2024-01-30 | 山东汇颐信息技术有限公司 | Industrial digital twin data space construction method, system, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7069269B2 (en) | Semi-supervised methods and systems for deep anomaly detection for large industrial surveillance systems based on time series data using digital twin simulation data | |
| US10915096B2 (en) | Method and system for quick customized-design of intelligent workshop | |
| Delgado et al. | Digital Twins for the built environment: learning from conceptual and process models in manufacturing | |
| CN110900307B (en) | Numerical control machine tool cutter monitoring system driven by digital twin | |
| CN109785180A (en) | A kind of scene perception system and method towards the twin workshop of number | |
| Safiyullah et al. | Prediction on performance degradation and maintenance of centrifugal gas compressors using genetic programming | |
| CN101408769A (en) | On-line energy forecasting system and method based on product ARIMA model | |
| CN112926257A (en) | Reciprocating natural gas compressor fault diagnosis system and diagnosis method | |
| Di Filippo et al. | Generative Design for project optimization (S). | |
| KR101328224B1 (en) | Virtual facility system for manufacturing steel and operating method thereof | |
| CN116880372A (en) | Operation optimization method and system of digital twin plant | |
| EP4033390A1 (en) | System and method for fault prediction and management of an asset | |
| CN116882038B (en) | Electromechanical construction method and system based on BIM technology | |
| CN115562225A (en) | Industrial robot operation and maintenance management method and device, computer equipment and storage medium | |
| CN105320805A (en) | Pico-satellite multi-source reliability information fusion method | |
| CN115438726A (en) | Device life and fault type prediction method and system based on digital twin technology | |
| CN116822115A (en) | Environment management method and system for intelligent park based on digital twin technology | |
| CN116756909A (en) | Early warning diagnosis system of thermal power plant based on data model and mechanism model | |
| Hatchett et al. | Real-time distribution system modeling: Development, application, and insights | |
| Ariansyah et al. | Digital twin development: a step by step guideline | |
| Kovalyov | Design and development of a power system digital twin: A model-based approach | |
| CN115618735A (en) | Facility structure health monitoring method based on digital twins and related device | |
| CN115034147A (en) | Intelligent manufacturing system based on digital twins | |
| WO2021111936A1 (en) | Prediction system, information processing device, and information processing program | |
| Williams et al. | Digital Twin of Cyber-Physical CNC for Smart Manufacturing |
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 |