CN117724419A - Method for constructing digital twin model, computer device and storage medium - Google Patents
Method for constructing digital twin model, computer device and storage medium Download PDFInfo
- Publication number
- CN117724419A CN117724419A CN202311715654.8A CN202311715654A CN117724419A CN 117724419 A CN117724419 A CN 117724419A CN 202311715654 A CN202311715654 A CN 202311715654A CN 117724419 A CN117724419 A CN 117724419A
- Authority
- CN
- China
- Prior art keywords
- operation parameter
- target
- environment
- parameter
- digital twin
- 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 49
- 238000004519 manufacturing process Methods 0.000 claims abstract description 146
- 230000007613 environmental effect Effects 0.000 claims description 39
- 238000004590 computer program Methods 0.000 claims description 26
- 238000012549 training Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008713 feedback mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/4185—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by the network communication
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- 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
- G05B2219/31—From computer integrated manufacturing till monitoring
- G05B2219/31088—Network communication between supervisor and cell, machine group
-
- 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)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Automation & Control Theory (AREA)
- Quality & Reliability (AREA)
- Manufacturing & Machinery (AREA)
- Feedback Control In General (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a method, a device, computer equipment and a storage medium for constructing a digital twin model. The method comprises the following steps: receiving an operation parameter sample set sent by a plurality of target devices; classifying the operation parameter sample sets according to the production batches to which each target device belongs to obtain operation parameter sample subsets of a plurality of production batches; classifying the operation parameter sample subsets of each production lot in the operation parameter sample subsets of the plurality of production lots according to the environment types matched with the environment parameter samples in the environment parameter sample sets to obtain operation parameter samples of a plurality of environment types in each production lot; the operation parameter samples of the plurality of environment types under each production batch are used for obtaining a digital twin model corresponding to each environment type under each production batch. By adopting the method, information sharing among devices is realized.
Description
Technical Field
The present disclosure relates to the field of device control technologies, and in particular, to a method for constructing a digital twin model, a computer device, and a storage medium.
Background
With the development of industrial technology, the degree of control of automation equipment is becoming higher and higher. In the process of controlling an automation device, a built-in negative feedback adjustment system is often adopted to adjust the operation parameters of the device so as to maintain the device in a normal operation state.
In the conventional art, a negative feedback adjustment system generally includes a sensor and a negative feedback adjustment circuit, and an operation parameter of a device is detected in real time by the sensor. When the operation parameter deviates from the preset value, the operation parameter is regulated by the negative feedback regulating circuit.
However, as the control method becomes more and more complex, a large number of sensors and negative feedback adjustment circuits are required to be installed when the conventional technology is adopted, resulting in higher control costs of the apparatus.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a method, an apparatus, a computer device, and a storage medium for constructing a digital twin model that can reduce the control cost of the device.
A method of constructing a digital twin model, the method comprising:
receiving an operation parameter sample set sent by a plurality of target devices;
classifying the operation parameter sample sets according to the production batches to which each target device belongs to obtain operation parameter sample subsets of a plurality of production batches;
Classifying the operation parameter sample subsets of each production lot in the operation parameter sample subsets of the plurality of production lots according to the environment types matched with the environment parameter samples in the environment parameter sample sets to obtain operation parameter samples of a plurality of environment types in each production lot; the operation parameter samples of the plurality of environment types under each production batch are used for obtaining a digital twin model corresponding to each environment type under each production batch.
In one embodiment, the method further comprises:
receiving environment parameter sample sets sent by the plurality of target devices;
classifying the operation parameter sample set according to the environment types matched with the environment parameter samples in the environment parameter sample set to obtain operation parameter samples of various environment types;
and training the plurality of initial digital twin models respectively by taking the operation parameter sample of each environment type in the operation parameter samples of the plurality of environment types as input data and taking the target operation parameter sample of the target equipment as output data to obtain the digital twin model corresponding to each environment type.
In one embodiment, the operation parameter sample subset is a set of at least one operation parameter sample, and the classifying the operation parameter sample subset of each production lot from the operation parameter sample subsets of the plurality of production lots to obtain operation parameter samples of a plurality of environmental types under each production lot includes:
Performing extraction-conversion-loading processing on the operation parameter sample set to obtain operation parameter sample subsets of a plurality of production batches;
classifying the operation parameter sample subsets of each production batch according to the environment types matched with the environment parameter samples in the environment parameter sample set to obtain operation parameter samples of various environment types in each production batch.
In one embodiment, the environment types include a strong electromagnetic operating environment, a high temperature operating environment, and a low temperature operating environment.
In one embodiment, the method further comprises:
acquiring a digital twin model matched with the target equipment; the digital twin model is obtained by training an initial digital twin model;
acquiring a first operation parameter acquired by the target equipment at the previous moment; the first operation parameter refers to parameter information generated when the target equipment operates;
inputting the first operation parameters into the digital twin model to obtain target operation parameters; the target operation parameter is the optimal operation parameter of the target equipment;
and determining a second operation parameter of the target equipment at the next moment according to the first operation parameter and the target operation parameter.
In one embodiment, the obtaining a digital twin model that matches the target device includes:
acquiring a digital twin model matched with a production batch to which the target equipment belongs and an environment parameter corresponding to the target equipment;
the step of inputting the first operation parameter to the digital twin model to obtain a target operation parameter includes:
and inputting the first operation parameter and the environment parameter into the digital twin model to obtain a target operation parameter.
In one embodiment, the determining, according to the first operation parameter and the target operation parameter, a second operation parameter of the target device at a next moment includes:
judging whether the first operation parameter and the target operation parameter meet preset conditions or not;
if not, calculating the deviation between the first operation parameter and the target operation parameter, and adjusting the first operation parameter according to the deviation to obtain an adjusted operation parameter;
inputting the adjusted operation parameters into the digital twin model to obtain adjusted target operation parameters;
and if the adjusted operation parameter and the adjusted target operation parameter meet the preset condition, determining the adjusted operation parameter as a second operation parameter of the target equipment at the next moment.
In one embodiment, the method further comprises:
obtaining a production batch to which the target equipment belongs;
obtaining the identification of other devices belonging to the production batch;
sharing a second operation parameter to the other equipment according to the identification so as to instruct the other equipment to operate according to the second operation parameter at the next moment;
alternatively, the operating parameters include operating parameters of the target component; the method further comprises the steps of:
acquiring the identification of other devices containing the target component;
and sharing the second operation parameters to the other equipment according to the identification so as to instruct a target component in the other equipment to operate according to the second operation parameters at the next moment.
An apparatus for determining an operating parameter, the apparatus comprising:
the receiving module is used for receiving the operation parameter sample sets sent by the plurality of target devices;
the classification module is used for classifying the operation parameter sample set according to the production batches to which each target device belongs to obtain operation parameter sample subsets of a plurality of production batches;
the construction module classifies the operation parameter sample subsets of each production batch in the operation parameter sample subsets of the plurality of production batches according to the environment types matched by the environment parameter samples in the environment parameter sample sets to obtain operation parameter samples of a plurality of environment types in each production batch; the operation parameter samples of the plurality of environment types under each production batch are used for obtaining a digital twin model corresponding to each environment type under each production batch.
A computer device comprising a memory storing a computer program and a processor which when executing the computer program performs the steps of:
receiving an operation parameter sample set sent by a plurality of target devices;
classifying the operation parameter sample sets according to the production batches to which each target device belongs to obtain operation parameter sample subsets of a plurality of production batches;
classifying the operation parameter sample subsets of each production lot in the operation parameter sample subsets of the plurality of production lots according to the environment types matched with the environment parameter samples in the environment parameter sample sets to obtain operation parameter samples of a plurality of environment types in each production lot; the operation parameter samples of the plurality of environment types under each production batch are used for obtaining a digital twin model corresponding to each environment type under each production batch.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
receiving an operation parameter sample set sent by a plurality of target devices;
classifying the operation parameter sample sets according to the production batches to which each target device belongs to obtain operation parameter sample subsets of a plurality of production batches;
Classifying the operation parameter sample subsets of each production lot in the operation parameter sample subsets of the plurality of production lots according to the environment types matched with the environment parameter samples in the environment parameter sample sets to obtain operation parameter samples of a plurality of environment types in each production lot; the operation parameter samples of the plurality of environment types under each production batch are used for obtaining a digital twin model corresponding to each environment type under each production batch.
The method for constructing the digital twin model, the computer equipment and the storage medium are used for receiving the operation parameter sample sets sent by the plurality of target equipment, classifying the operation parameter sample sets according to the production batches to which each target equipment belongs, and obtaining operation parameter sample subsets of the plurality of production batches; classifying the operation parameter sample subsets of each production batch in the operation parameter sample subsets of a plurality of production batches according to the environment types matched with the environment parameters in the environment parameter sample sets to obtain operation parameter samples of a plurality of environment types in each production batch; the operation parameter samples of the plurality of environment types under each production batch are used for obtaining a digital twin model corresponding to each environment type under each production batch. When the method is used for establishing the digital twin model, the corresponding digital twin model is established under different environmental scenes for each production batch, and the model can receive and feed back target operation parameters of each device under the same environmental scene of the same production batch, so that information sharing among the devices is realized.
Drawings
FIG. 1 is an application environment diagram of a method of constructing a digital twin model in one embodiment;
FIG. 2 is a flow diagram of a method of constructing a digital twin model in one embodiment;
FIG. 3 is a flow diagram of a training method of a digital twin model in one embodiment;
FIG. 4 is a flow chart illustrating the steps for determining an operational parameter sample in one embodiment;
FIG. 5 is a flow chart illustrating the steps for determining a second operating parameter in one embodiment;
fig. 6 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The construction method of the digital twin model provided by the application can be applied to an application environment shown in figure 1. Wherein the target device 102 communicates with the server 104 via a network. The server 104 receives the operation parameter sample sets sent by the plurality of target devices; classifying the operation parameter sample sets according to the production batches to which each target device belongs to obtain operation parameter sample subsets of a plurality of production batches; classifying the operation parameter sample subsets of each production lot in the operation parameter sample subsets of a plurality of production lots according to the environment types matched with the environment parameter samples in the environment parameter sample sets to obtain operation parameter samples of a plurality of environment types in each production lot; the operating parameter samples of the plurality of environmental types for each production lot are used to derive a digital twinning model for each production lot corresponding to each environmental type. The target device 102 may be, but not limited to, an industrial device and a home device, and the server 104 may be implemented as a stand-alone server or a server cluster composed of a plurality of servers.
In one embodiment, a method of constructing a digital twin model is provided. As shown in fig. 2, on the basis of the above embodiment, the method may be specifically implemented by the following steps:
step 202, receiving operation parameter sample sets sent by a plurality of target devices;
based on this, the method further comprises the steps of:
step 204, classifying the operation parameter sample set according to the production lot to which each target device belongs, to obtain operation parameter sample subsets of a plurality of production lots;
step 206, classifying the operation parameter sample subset of each production lot from the operation parameter sample subsets of a plurality of production lots according to the environment types matched by the environment parameter samples in the environment parameter sample set, so as to obtain the operation parameter samples of a plurality of environment types in each production lot.
The operation parameter samples of the plurality of environment types under each production batch are used for obtaining a digital twin model corresponding to each environment type under each production batch.
Wherein the set of operating parameter samples is a set of at least one operating parameter sample. An environmental parameter sample set is a set of at least one environmental parameter sample. The operation parameter samples and the environment parameter samples collected by the same target equipment at the same time have a corresponding relationship.
Specifically, each of the plurality of target devices uploads the operating parameter sample set and the environmental parameter sample set to a big data center of the server through an internet of things (Internet of Things, IOT) protocol. And then the server classifies the operation parameter samples corresponding to the environment parameter samples according to the environment types matched with the environment parameter samples in the environment parameter sample set to obtain operation parameter samples of various environment types. And finally, aiming at each environment type, taking a corresponding operation parameter sample as input data, taking a corresponding target operation parameter sample of target equipment as output data, and training at least one initial digital twin model to obtain a digital twin model corresponding to each environment type. It is understood that one environment type corresponds to at least one digital twinning model.
In this embodiment, all devices may realize information sharing through an internet of things protocol, and then through deep learning on training data generated by the devices, different digital twin models are built according to different environments, so that the digital twin models have environmental diversity, and meanwhile, digital twin models corresponding to the devices in different environments are continuously optimized, so as to create and perfect an operation growth model belonging to the devices. The feedback mechanism of the equipment control is continuously perfected through deep learning, and the equipment is energized.
In one embodiment, as shown in fig. 3, the method further comprises:
in step 302, a set of environmental parameter samples sent by a plurality of target devices is received.
Step 304, classifying the operation parameter sample set according to the environment types matched with the environment parameter samples in the environment parameter sample set to obtain operation parameter samples with various environment types.
Step 306, taking the operation parameter sample of each environment type in the operation parameter samples of the plurality of environment types as input data, taking the target operation parameter sample of the target device as output data, and respectively training the plurality of initial digital twin models to obtain the digital twin model corresponding to each environment type.
The steps 302 to 306 may be implemented by the following steps:
taking an operation parameter sample of each environment type in operation parameter samples of a plurality of environment types in each production batch as input data, taking a target operation parameter sample of target equipment as output data, and respectively training a plurality of initial digital twin models to obtain digital twin models corresponding to each environment type in each production batch.
Specifically, the server trains at least one initial digital twin model by taking a corresponding operation parameter sample of each environment type in each production batch as input data and taking a target operation parameter sample of target equipment as output data, so as to obtain the digital twin model corresponding to each environment type in each production batch. It will be appreciated that in each production lot, one environment type corresponds to at least one digital twinning model.
Further, the server trains at least one initial digital twin model by taking the corresponding operation parameter sample and the environment parameter sample of each production batch as input data and taking the target operation parameter sample of the equipment as output data to obtain the digital twin model corresponding to each environment type in each production batch.
In this embodiment, when a digital twin model is established, for each production lot, a corresponding digital twin model is established in different environmental scenes, and the model receives and feeds back target operation parameters of each device in the same environmental scene of the same production lot, thereby realizing information sharing between the devices.
In one embodiment, the subset of operating parameter samples is a collection of at least one operating parameter sample, as shown in FIG. 4, and the particular process of step 206 includes the steps of:
step 401, performing extraction-conversion-loading processing on the operation parameter sample set to obtain operation parameter sample subsets of a plurality of production lots.
Step 402, classifying the operation parameter sample subset of each production lot according to the environment types matched by the environment parameter samples in the environment parameter sample set, so as to obtain operation parameter samples of multiple environment types in each production lot.
Specifically, the server classifies the operation parameter sample sets according to production batches to which the equipment belongs, and obtains operation parameter sample subsets of a plurality of production batches. Optionally, the server performs an Extract-Transform-Load (ETL) process on the set of operating parameter samples to obtain a subset of operating parameter samples for the plurality of production lots. Then, the server classifies the operation parameter sample subset of each production lot in the operation parameter sample subsets of a plurality of production lots again according to the environment types matched by the environment parameter samples in the environment parameter sample set to obtain operation parameter samples of a plurality of environment types in each production lot, and the operation parameter samples are classified.
Further, the server classifies the operation parameter sample set and the environment parameter sample set according to the production batches to which the equipment belongs, so as to obtain operation parameter sample subsets and environment parameter sample subsets of a plurality of production batches. And then, the server classifies the operation parameter sample subset and the environment parameter sample subset of each production lot in the operation parameter sample subsets of a plurality of production lots again according to the environment types matched by the environment parameter samples in the environment parameter sample set to obtain operation parameter samples and environment parameter samples of a plurality of environment types under each production lot. Then, using a distributed computing engine spark to take the 'production batch-monitoring component' as a unique identifier, and acquiring the operation parameters of each dimension of the identifier, such as: days of operation, etc. Each dimension name and dimension value serves as a label.
In one embodiment, the environment types include a strong electromagnetic operating environment, a high temperature operating environment, and a low temperature operating environment.
In one embodiment, as shown in fig. 5, the method further comprises:
step 501, a digital twin model is obtained that matches a target device.
The digital twin model is obtained by training an initial digital twin model.
Specifically, the server obtains a digital twin model that matches the target device. Optionally, the server obtains a digital twin model that matches the identity of the target device. Optionally, the server obtains a digital twinning model that matches the production lot to which the target device belongs. Optionally, the server obtains a digital twin model that matches the environmental parameters corresponding to the target device. Specifically, the server determines an environment type from the environment parameters, and obtains a digital twin model associated with the environment type. Optionally, the server matches the environmental parameters with parameter intervals corresponding to the plurality of environmental types, thereby obtaining the environmental type successfully matched with the environmental parameters. The environment type may be, for example, a strong electromagnetic operating environment, a high temperature operating environment, a low temperature operating environment, and the like. Each environment type is provided with an associated digital twin model. Thus, after determining the type of environment for which the environmental parameter match was successful, a digital twin model that matches the environmental parameter may be further determined.
Step 502, acquiring a first operation parameter acquired by a target device at the previous moment; the first operation parameter refers to parameter information generated when the target device is operated.
The operation parameters refer to parameter information generated when the target equipment operates. For example, the operating parameters may include operating speed, operating power, rotational speed, and the like.
Specifically, the target device may collect a first operation parameter of itself at a previous time through a built-in sensor, and upload the first operation parameter to the server. The server thus obtains the first operating parameter collected by the target device at the last moment. Optionally, the server uses distributed streaming computing to monitor log data of the target device in real time, where the log data includes the first operating parameter. In one embodiment, a server obtains a first operating parameter and an environmental parameter collected by a target device at a previous time.
Step 503, inputting the first operation parameter into the digital twin model to obtain the target operation parameter.
The digital twin model is obtained by training an initial digital twin model by taking operation parameter samples of a plurality of devices as input data and target operation parameter samples of the plurality of devices as output data.
Specifically, the server inputs the first operating parameter to a digital twin model, which outputs the target operating parameter. Alternatively, the target operating parameter may be an optimal operating parameter.
Step 504, determining a second operation parameter of the target device at the next moment according to the first operation parameter and the target operation parameter.
Specifically, the server determines a second operation parameter of the target device at a next moment according to the first operation parameter and the target operation parameter. Optionally, the server adjusts the first operation parameter according to the deviation between the first operation parameter and the target operation parameter until the proximity between the first operation parameter and the target operation parameter meets a preset condition. And then, the server generates a remote instruction according to the second operation parameter and sends the remote instruction to the target equipment. And the target equipment receives the remote instruction and analyzes the remote instruction to obtain a second operation parameter, and operates according to the second operation parameter at the next moment. Thereby achieving the purpose of autonomous regulation.
In this embodiment, based on a digital twin model matched with the target device, the first operation parameter of the target device at a previous time is processed, the target operation parameter of the target device is determined, and then the second operation parameter of the target device at a next time is determined, and then the target device can operate according to the second operation parameter at the next time. Therefore, a large number of sensors and negative feedback regulating circuits are not required to be installed in the equipment, the occupied space and the hardware cost are saved, and the control cost of the equipment is reduced.
In one embodiment, the specific processing procedure of step 501 in the foregoing embodiment includes the following steps:
step 5011, obtaining a digital twin model matched with the production batch to which the target equipment belongs and the environmental parameters corresponding to the target equipment.
The environmental parameter refers to parameter information of the surrounding environment where the target device is located. For example, environmental parameters may include air humidity, air ph, temperature, electromagnetic strength, equipment current stability, and the like.
Wherein, the digital twin model establishes an association relation with the production batch (such as equipment model) and the environment type in advance.
Specifically, the environmental parameters around the target device at the previous time may be monitored by the environmental monitor, and uploaded to the server. The server determines an environment type based on the environment parameter, and obtains a digital twin model associated with the environment type and the production lot.
Based on this, in one embodiment, one possible implementation of the above-described step S503 "inputting the first operating parameter to the digital twin model, resulting in the target operating parameter" is referred to. On the basis of the above embodiment, step S503 may be specifically implemented by the following steps:
In step S5031, the first operation parameter and the environmental parameter are input to the digital twin model to obtain the target operation parameter.
The digital twin model is obtained by training an initial digital twin model by taking operation parameter samples and environment parameter samples of a plurality of devices as input data and taking target operation parameter samples of the plurality of devices as output data.
Specifically, the server inputs the first operating parameter and the environmental parameter to a digital twin model, which outputs the target operating parameter. Alternatively, the target operating parameter may be an optimal operating parameter.
In this embodiment, the digital twin model is determined based on the production lot and the environmental parameters, so that the accuracy of the target operation parameters can be improved.
In one embodiment, one possible implementation of the above-described step 504 "determining the second operating parameter of the target device at the next time based on the first operating parameter and the target operating parameter" is referred to. Based on the above embodiment, the step 504 may be specifically implemented by the following steps:
step 5041, judging whether the first operation parameter and the target operation parameter meet preset conditions;
step 5042, if not, calculating a deviation between the first operation parameter and the target operation parameter, and adjusting the first operation parameter according to the deviation to obtain an adjusted operation parameter;
Step 5043, inputting the adjusted operation parameters to the digital twin model to obtain adjusted target operation parameters;
in step 5044, if the adjusted operation parameter and the adjusted target operation parameter meet the preset condition, the adjusted operation parameter is determined as the second operation parameter of the target device at the next moment.
Specifically, the server determines whether the first operation parameter and the target operation parameter satisfy a preset condition. The preset condition is used to ensure proximity between the operating parameters. Alternatively, the preset condition may be that the deviation between the operating parameters is less than a deviation threshold. The deviation threshold may be, for example, 0.95. The preset condition may also be that the ratio between the operating parameters lies within a ratio interval. The ratio interval may be, for example, [0.99,1.01].
And then, if the server judges that the first operation parameter and the target operation parameter meet the preset conditions, determining the first operation parameter as a second operation parameter of the target equipment at the next moment. If the server judges that the first operation parameter and the target operation parameter do not meet the preset condition, calculating the deviation between the first operation parameter and the target operation parameter, and adjusting the first operation parameter according to the deviation to obtain the adjusted operation parameter. Optionally, the first operation parameter may be adjusted according to the deviation by adding the first operation parameter to the deviation, or adding the first operation parameter to a preset adjustment value, or multiplying the deviation by a preset coefficient, and then adding the first operation parameter to the multiplication result.
And then, the server inputs the adjusted operation parameters into the digital twin model to obtain the adjusted target operation parameters.
And finally, the server judges whether the adjusted operation parameters and the adjusted target operation parameters meet preset conditions. If yes, the adjusted operation parameters are determined to be second operation parameters of the target equipment at the next moment. If not, the process returns to step 5043 until the adjusted operating parameter and the adjusted target operating parameter meet the preset condition. I.e. until all the indexes of the target equipment are in the optimal state.
In this embodiment, by continuously adjusting the operation parameters, it is ensured that the target device and other devices are always in an optimal operation state.
In one embodiment, one possible implementation of step S501 "acquire digital twin model matched to target device" described above is involved. On the basis of the above embodiment, step S501 may be specifically implemented by the following steps:
in one embodiment, the method further comprises the steps of:
step 212, obtaining a production batch to which the target equipment belongs;
step 214, obtaining the identification of other devices belonging to the production lot;
and step 216, sharing the second operation parameters to other devices according to the identification to instruct the other devices to operate according to the second operation parameters at the next moment.
Specifically, the server obtains the production lot to which the target device belongs, searches for the identifiers of other devices belonging to the production lot, and shares the second operation parameters to the other devices. And the other equipment receives the second operation parameters and operates according to the second operation parameters at the next moment.
In this embodiment, considering that the hardware structures of the devices in the same batch are the same or close to each other, the operation parameters can be shared for use, so that when modeling, a corresponding digital twin model is built for each production batch, and after determining the second operation parameters based on the digital twin model, the second operation parameters can be shared for use with other devices in the same batch, so that the calculation resources can be saved.
Alternatively, the operating parameters include operating parameters of the target component. Based on this, in one embodiment, the method further comprises the steps of:
step 222, obtaining the identification of other devices containing the target component;
step 224, sharing the second operation parameter to other devices according to the identification, so as to instruct the target component in the other devices to operate according to the second operation parameter at the next moment.
Wherein the component is an assembly unit in the device. For example, the components may include motors, rotating components, and the like.
Specifically, the server obtains the identifier of the other device including the target component, and then shares the second operation parameter to the other device according to the identifier. And the other equipment receives the second operation parameters and controls the target component to operate according to the second operation parameters at the next moment.
In this embodiment, the operating parameters of the devices having the same components may be shared, so that after determining the second operating parameters of the target device based on the digital twin model, the second operating parameters may be shared with other devices having the same components, which is beneficial to saving computing resources.
It should be understood that, although the steps in the flowcharts of fig. 2-3 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 2-3 may include multiple steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the steps or stages in other steps or other steps.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 6. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by a processor, implements a method of constructing a digital twin model.
It will be appreciated by those skilled in the art that the structure shown in fig. 6 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
receiving an operation parameter sample set sent by a plurality of target devices;
classifying the operation parameter sample sets according to the production batches to which each target device belongs to obtain operation parameter sample subsets of a plurality of production batches;
classifying the operation parameter sample subsets of each production lot in the operation parameter sample subsets of a plurality of production lots according to the environment types matched with the environment parameter samples in the environment parameter sample sets to obtain operation parameter samples of a plurality of environment types in each production lot; the operating parameter samples of the plurality of environmental types for each production lot are used to derive a digital twinning model for each production lot corresponding to each environmental type.
In the computer equipment, when the digital twin model is built, the corresponding digital twin model is built under different environmental scenes for each production batch, and the model can receive and feed back the target operation parameters of each equipment under the same environmental scene of the same production batch, so that information sharing among the equipment is realized.
In one embodiment, the processor when executing the computer program further performs the steps of:
receiving environment parameter sample sets sent by a plurality of target devices;
classifying the operation parameter sample set according to the environment types matched with the environment parameter samples in the environment parameter sample set to obtain operation parameter samples of various environment types;
taking an operation parameter sample of each environment type in the operation parameter samples of the plurality of environment types as input data, taking a target operation parameter sample of target equipment as output data, and respectively training a plurality of initial digital twin models to obtain digital twin models corresponding to each environment type.
In one embodiment, the processor when executing the computer program further performs the steps of:
performing extraction-conversion-loading processing on the operation parameter sample set to obtain operation parameter sample subsets of a plurality of production batches;
classifying the operation parameter sample subsets of each production batch according to the environment types matched with the environment parameter samples in the environment parameter sample set to obtain operation parameter samples of various environment types in each production batch.
In one embodiment, the processor when executing the computer program further performs the steps of:
Acquiring a digital twin model matched with target equipment; the digital twin model is obtained by training an initial digital twin model;
acquiring a first operation parameter acquired by target equipment at the last moment; the first operation parameter refers to parameter information generated when the target equipment operates;
inputting the first operation parameters into a digital twin model to obtain target operation parameters; the target operation parameter is the optimal operation parameter of the target equipment;
and determining a second operation parameter of the target equipment at the next moment according to the first operation parameter and the target operation parameter.
In one embodiment, the processor when executing the computer program further performs the steps of:
acquiring a digital twin model matched with production batches to which target equipment belongs and environmental parameters corresponding to the target equipment;
inputting the first operation parameter into the digital twin model to obtain a target operation parameter, wherein the method comprises the following steps:
and inputting the first operation parameters and the environment parameters into the digital twin model to obtain target operation parameters.
In one embodiment, the processor when executing the computer program further performs the steps of:
judging whether the first operation parameter and the target operation parameter meet preset conditions or not;
If not, calculating the deviation between the first operation parameter and the target operation parameter, and adjusting the first operation parameter according to the deviation to obtain an adjusted operation parameter;
inputting the adjusted operation parameters into a digital twin model to obtain adjusted target operation parameters;
and if the adjusted operation parameters and the adjusted target operation parameters meet the preset conditions, determining the adjusted operation parameters as second operation parameters of the target equipment at the next moment.
In one embodiment, the processor when executing the computer program further performs the steps of:
obtaining a production batch to which target equipment belongs;
obtaining the identification of other devices belonging to the same production batch;
sharing the second operation parameters to other devices according to the identification to instruct the other devices to operate according to the second operation parameters at the next moment;
alternatively, the operating parameters include operating parameters of the target component;
acquiring the identification of other devices containing the target component;
and sharing the second operation parameters to other devices according to the identification to instruct the target components in the other devices to operate according to the second operation parameters at the next moment.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
Receiving an operation parameter sample set sent by a plurality of target devices;
classifying the operation parameter sample sets according to the production batches to which each target device belongs to obtain operation parameter sample subsets of a plurality of production batches;
classifying the operation parameter sample subsets of each production lot in the operation parameter sample subsets of a plurality of production lots according to the environment types matched with the environment parameter samples in the environment parameter sample sets to obtain operation parameter samples of a plurality of environment types in each production lot; the operating parameter samples of the plurality of environmental types for each production lot are used to derive a digital twinning model for each production lot corresponding to each environmental type.
In the above computer-readable storage medium, when the digital twin model is built, for each production lot, a corresponding digital twin model is built in different environmental scenes, and the model can accept and feed back the target operation parameters of each device in the same environmental scene of the same production lot, thereby realizing information sharing among the devices.
In one embodiment, the computer program when executed by the processor further performs the steps of:
receiving environment parameter sample sets sent by a plurality of target devices;
Classifying the operation parameter sample set according to the environment types matched with the environment parameter samples in the environment parameter sample set to obtain operation parameter samples of various environment types;
taking an operation parameter sample of each environment type in the operation parameter samples of the plurality of environment types as input data, taking a target operation parameter sample of target equipment as output data, and respectively training a plurality of initial digital twin models to obtain digital twin models corresponding to each environment type.
In one embodiment, the computer program when executed by the processor further performs the steps of:
performing extraction-conversion-loading processing on the operation parameter sample set to obtain operation parameter sample subsets of a plurality of production batches;
classifying the operation parameter sample subsets of each production batch according to the environment types matched with the environment parameter samples in the environment parameter sample set to obtain operation parameter samples of various environment types in each production batch.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring a digital twin model matched with target equipment; the digital twin model is obtained by training an initial digital twin model;
Acquiring a first operation parameter acquired by target equipment at the last moment; the first operation parameter refers to parameter information generated when the target equipment operates;
inputting the first operation parameters into a digital twin model to obtain target operation parameters; the target operation parameter is the optimal operation parameter of the target equipment;
and determining a second operation parameter of the target equipment at the next moment according to the first operation parameter and the target operation parameter.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring a digital twin model matched with production batches to which target equipment belongs and environmental parameters corresponding to the target equipment;
and inputting the first operation parameters and the environment parameters into the digital twin model to obtain target operation parameters.
In one embodiment, the computer program when executed by the processor further performs the steps of:
judging whether the first operation parameter and the target operation parameter meet preset conditions or not;
if not, calculating the deviation between the first operation parameter and the target operation parameter, and adjusting the first operation parameter according to the deviation to obtain an adjusted operation parameter;
inputting the adjusted operation parameters into a digital twin model to obtain adjusted target operation parameters;
And if the adjusted operation parameters and the adjusted target operation parameters meet the preset conditions, determining the adjusted operation parameters as second operation parameters of the target equipment at the next moment.
In one embodiment, the computer program when executed by the processor further performs the steps of:
obtaining a production batch to which target equipment belongs;
obtaining the identification of other devices belonging to the same production batch;
sharing the second operation parameters to other devices according to the identification to instruct the other devices to operate according to the second operation parameters at the next moment;
alternatively, the operating parameters include operating parameters of the target component;
acquiring the identification of other devices containing the target component;
and sharing the second operation parameters to other devices according to the identification to instruct the target components in the other devices to operate according to the second operation parameters at the next moment.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, or the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like.
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 merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (10)
1. A method of constructing a digital twin model, the method comprising:
receiving an operation parameter sample set sent by a plurality of target devices;
classifying the operation parameter sample sets according to the production batches to which each target device belongs to obtain operation parameter sample subsets of a plurality of production batches;
classifying the operation parameter sample subsets of each production lot in the operation parameter sample subsets of the plurality of production lots according to the environment types matched with the environment parameter samples in the environment parameter sample sets to obtain operation parameter samples of a plurality of environment types in each production lot; the operation parameter samples of the plurality of environment types under each production batch are used for obtaining a digital twin model corresponding to each environment type under each production batch.
2. The method according to claim 1, wherein the method further comprises:
receiving environment parameter sample sets sent by the plurality of target devices;
classifying the operation parameter sample set according to the environment types matched with the environment parameter samples in the environment parameter sample set to obtain operation parameter samples of various environment types;
and training the plurality of initial digital twin models respectively by taking the operation parameter sample of each environment type in the operation parameter samples of the plurality of environment types as input data and taking the target operation parameter sample of the target equipment as output data to obtain the digital twin model corresponding to each environment type.
3. The method of claim 1, wherein the subset of operating parameter samples is a set of at least one operating parameter sample, and wherein classifying the subset of operating parameter samples for each of the plurality of production lots to obtain a plurality of environmental types of operating parameter samples for each production lot comprises:
performing extraction-conversion-loading processing on the operation parameter sample set to obtain operation parameter sample subsets of a plurality of production batches;
Classifying the operation parameter sample subsets of each production batch according to the environment types matched with the environment parameter samples in the environment parameter sample set to obtain operation parameter samples of various environment types in each production batch.
4. The method of claim 1, wherein the environment types include a strong electromagnetic operating environment, a high temperature operating environment, and a low temperature operating environment.
5. The method according to claim 1, wherein the method further comprises:
acquiring a digital twin model matched with the target equipment; the digital twin model is obtained by training an initial digital twin model;
acquiring a first operation parameter acquired by the target equipment at the previous moment; the first operation parameter refers to parameter information generated when the target equipment operates;
inputting the first operation parameters into the digital twin model to obtain target operation parameters; the target operation parameter is the optimal operation parameter of the target equipment;
and determining a second operation parameter of the target equipment at the next moment according to the first operation parameter and the target operation parameter.
6. The method of claim 5, wherein the obtaining a digital twin model that matches the target device comprises:
Acquiring a digital twin model matched with a production batch to which the target equipment belongs and an environment parameter corresponding to the target equipment;
the step of inputting the first operation parameter to the digital twin model to obtain a target operation parameter includes:
and inputting the first operation parameter and the environment parameter into the digital twin model to obtain a target operation parameter.
7. The method of claim 5, wherein determining a second operating parameter of the target device at a next time based on the first operating parameter and the target operating parameter comprises:
judging whether the first operation parameter and the target operation parameter meet preset conditions or not;
if not, calculating the deviation between the first operation parameter and the target operation parameter, and adjusting the first operation parameter according to the deviation to obtain an adjusted operation parameter;
inputting the adjusted operation parameters into the digital twin model to obtain adjusted target operation parameters;
and if the adjusted operation parameter and the adjusted target operation parameter meet the preset condition, determining the adjusted operation parameter as a second operation parameter of the target equipment at the next moment.
8. The method of claim 1, 2 or 5, further comprising:
obtaining a production batch to which the target equipment belongs;
obtaining the identification of other devices belonging to the production batch;
sharing a second operation parameter to the other equipment according to the identification so as to instruct the other equipment to operate according to the second operation parameter at the next moment;
alternatively, the operating parameters include operating parameters of the target component; the method further comprises the steps of:
acquiring the identification of other devices containing the target component;
and sharing the second operation parameters to the other equipment according to the identification so as to instruct a target component in the other equipment to operate according to the second operation parameters at the next moment.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 8 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311715654.8A CN117724419A (en) | 2021-09-14 | 2021-09-14 | Method for constructing digital twin model, computer device and storage medium |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311715654.8A CN117724419A (en) | 2021-09-14 | 2021-09-14 | Method for constructing digital twin model, computer device and storage medium |
| CN202111074353.2A CN113805544B (en) | 2021-09-14 | 2021-09-14 | Method, device, computer equipment and storage medium for determining operation parameters |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111074353.2A Division CN113805544B (en) | 2021-09-14 | 2021-09-14 | Method, device, computer equipment and storage medium for determining operation parameters |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117724419A true CN117724419A (en) | 2024-03-19 |
Family
ID=78895231
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111074353.2A Active CN113805544B (en) | 2021-09-14 | 2021-09-14 | Method, device, computer equipment and storage medium for determining operation parameters |
| CN202311715654.8A Pending CN117724419A (en) | 2021-09-14 | 2021-09-14 | Method for constructing digital twin model, computer device and storage medium |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111074353.2A Active CN113805544B (en) | 2021-09-14 | 2021-09-14 | Method, device, computer equipment and storage medium for determining operation parameters |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN113805544B (en) |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10360318B2 (en) * | 2014-09-22 | 2019-07-23 | Pratt & Whitney Canada Corp. | System and method for multi-domain graphical modeling |
| EP3997475A4 (en) * | 2019-07-08 | 2023-07-19 | Strong Force VCN Portfolio 2019, LLC | Systems and methods for detecting occupancy using radio signals |
| CN110530638B (en) * | 2019-07-31 | 2020-10-27 | 西安交通大学 | Digital twin-based method for detecting and diagnosing damage of main bearing of aero-engine |
| CN111310318A (en) * | 2020-02-05 | 2020-06-19 | 北京理工大学 | Digital twinning-based process margin processing method and system and mechanical manufacturing assembly |
| CN112381412B (en) * | 2020-11-16 | 2023-04-07 | 北京航空航天大学 | Digital twin satellite pulsating type general assembly distributed management and control system |
| CN112416783B (en) * | 2020-11-25 | 2022-05-20 | 武汉联影医疗科技有限公司 | Method, device, equipment and storage medium for determining software quality influence factors |
| CN113146632A (en) * | 2021-04-20 | 2021-07-23 | 北京洛必德科技有限公司 | Household robot control method and system based on digital twin technology |
-
2021
- 2021-09-14 CN CN202111074353.2A patent/CN113805544B/en active Active
- 2021-09-14 CN CN202311715654.8A patent/CN117724419A/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| CN113805544B (en) | 2023-10-31 |
| CN113805544A (en) | 2021-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111445007A (en) | Training method and system for resisting generation of neural network | |
| CN111109105A (en) | Pet feeding method and device, computer equipment and storage medium | |
| CN112183750A (en) | Neural network model training method and device, computer equipment and storage medium | |
| CN113805544B (en) | Method, device, computer equipment and storage medium for determining operation parameters | |
| CN116963482B (en) | Intelligent energy-saving method and related equipment based on data center heating and ventilation system | |
| CN114119289A (en) | Method and device for processing comprehensive energy monitoring data | |
| CN117260035A (en) | Power control method and system of handheld laser welding machine | |
| CN116954334A (en) | Heat dissipation control method, device, server, computer equipment and storage medium | |
| CN111698321A (en) | Internet of things equipment data synchronization method and device and control center | |
| CN116560828A (en) | Task processing method, device, computer equipment, storage medium and program product | |
| CN114726002A (en) | Virtual control-based multi-generator-set output control method and system | |
| CN113570473B (en) | Equipment fault monitoring method, device, computer equipment and storage medium | |
| CN113448747B (en) | Data transmission method, device, computer equipment and storage medium | |
| CN114720128A (en) | Electromagnetic bearing control method, device and system | |
| EP4174593A1 (en) | Method for operating a device in an iot system | |
| US20200065508A1 (en) | Device and method to share image received from user terminal with other user terminals | |
| CN110874465B (en) | Mobile equipment entity identification method and device based on semi-supervised learning algorithm | |
| CN111985446A (en) | Face recognition method and system | |
| CN211087029U (en) | Device for realizing remote multi-greenhouse environment control based on Internet of things | |
| CN116738185B (en) | AI algorithm construction method for intelligent cultivation | |
| CN114115490A (en) | Fan regulation and control method, system, equipment and medium of server | |
| CN115225575B (en) | Unknown network flow classification method based on metadata assistance and federal learning | |
| CN117557870B (en) | Classification model training method and system based on federal learning client selection | |
| CN114090674A (en) | Power data processing method and device and power data system | |
| EP3771997A1 (en) | System, method, and program |
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 |