CN113868898A - Data processing method and device based on digital twin model - Google Patents
Data processing method and device based on digital twin model Download PDFInfo
- Publication number
- CN113868898A CN113868898A CN202111427677.XA CN202111427677A CN113868898A CN 113868898 A CN113868898 A CN 113868898A CN 202111427677 A CN202111427677 A CN 202111427677A CN 113868898 A CN113868898 A CN 113868898A
- Authority
- CN
- China
- Prior art keywords
- digital twin
- twin model
- target
- scheme
- model
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Computer Graphics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Feedback Control In General (AREA)
Abstract
The application discloses a data processing method and a data processing device based on a digital twin model, wherein the method comprises the following steps: acquiring first attribute information of first equipment in a physical space; constructing a digital twin model for simulating the first device in the virtual space based on the first attribute information; controlling the first equipment to operate based on the first operation scheme, and acquiring first actual operation data generated in the operation process of the first equipment; controlling the digital twin model to operate based on the first operation scheme, and acquiring first virtual operation data generated in the operation process of the digital twin model; and in the case that the error between the first virtual operation data and the first actual operation data is larger than a first threshold value, correcting the digital twin model so as to enable the simulation degree of the digital twin model to accord with the simulation condition. The method can keep higher consistency of the first equipment and the digital twin model, and is beneficial to improving the accuracy of the simulation result of the digital twin model.
Description
Technical Field
The application relates to the technical field of production equipment control, in particular to a data processing method and device based on a digital twin model.
Background
The digital twin model is used for simulating the equipment in the physical space, for example, simulating the operation process of the equipment. The operation state of the equipment is dynamically changed during the operation of the equipment in the physical space, for example, the equipment gradually ages along with the increase of the use time, and the operation state of the equipment is also dynamically changed along with the change of the use environment during the operation of the equipment. However, the digital twin model in the virtual space is not influenced by the environment and the running time, the consistency of the digital twin model and the equipment changes along with the time, and the consistency of the digital twin model and the equipment directly influences the simulation result. Therefore, how to keep the consistency of the digital twin model and the devices in the physical space high continuously becomes a technical problem to be solved by those skilled in the art.
Disclosure of Invention
The application provides a data processing method and device based on a digital twin model, and the technical scheme adopted by the embodiment of the application is as follows:
one aspect of the present application provides a data processing method based on a digital twin model, including:
acquiring first attribute information of first equipment in a physical space;
constructing a digital twin model for simulating the first device in a virtual space based on the first attribute information;
controlling the first equipment to operate based on a first operation scheme, and acquiring first actual operation data generated in the operation process of the first equipment; wherein the first actual operational data characterizes operational performance of the first device;
controlling the digital twin model to operate based on the first operation scheme, and acquiring first virtual operation data generated in the operation process of the digital twin model; wherein the first virtual operating data characterizes operating performance of the digital twin model;
and under the condition that the error between the first virtual operation data and the first actual operation data is larger than a first threshold value, correcting the digital twin model so as to enable the simulation degree of the digital twin model to accord with the simulation condition.
In some embodiments, the correcting the digital twin model to make the simulation degree of the digital twin model meet the simulation condition includes:
supplementarily acquiring second attribute information of the first device in the physical space;
and correcting the digital twin model based on the second attribute information so that the simulation degree of the corrected digital twin model meets the simulation condition.
In some embodiments, the method further comprises:
acquiring a target scheme by utilizing the digital twin model based on set target operation data; wherein the target operating data characterizes a target operating performance of the digital twin model, the target scheme being for controlling the digital twin model to operate and conforming the digital twin model to the target operating performance;
and controlling the first equipment to operate based on the target scheme.
In some embodiments, the obtaining a target solution using the digital twin model based on the set target operating data includes:
based on the target operation data, utilizing a mechanism model capable of representing the operation mechanism of the digital twin model to obtain at least one second operation scheme; wherein the mechanism model is a machine learning model;
controlling the digital twin model to operate based on each second operation scheme, and acquiring second virtual operation data generated in the operation process of the digital twin model;
and under the condition that the second virtual operation data accords with the target operation data, determining the corresponding second operation scheme as a first target scheme.
In some embodiments, the method further comprises:
acquiring second actual operation data generated in the operation process of the first equipment based on the first target scheme;
training the mechanism model based on the second actual operating data and the first target scenario when an error between the second actual operating data and the target operating data is greater than a second threshold;
acquiring at least one third operation scheme by utilizing the trained mechanism model based on the target operation data;
controlling the digital twin model to operate based on each third operation scheme, and acquiring third virtual operation data generated in the operation process of the digital twin model;
determining the corresponding third operation scheme as a second target scheme under the condition that the third virtual operation data conforms to the target operation data;
and controlling the first equipment to operate based on the second target scheme, acquiring third actual operation data generated in the operation process of the first equipment, and iterating until the error between the third actual operation data and the target operation data is smaller than the second threshold value.
In some embodiments, said controlling said first device to operate based on said target scheme comprises:
generating control instructions for controlling each operation process of the first equipment based on the target scheme, and forming an instruction set containing each control instruction;
sending the instruction set to an edge controller, wherein the instruction set is used for causing the edge controller to control the first device to operate based on the instruction set.
Another aspect of the present application provides a data processing apparatus based on a digital twin model, including:
the device comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring first attribute information of first equipment in a physical space;
a building module, configured to build a digital twin model for simulating the first device in a virtual space based on the first attribute information;
the first control module is used for controlling the first equipment to operate based on a first operation scheme and acquiring first actual operation data generated in the operation process of the first equipment; wherein the first actual operational data characterizes operational performance of the first device;
the second control module is used for controlling the digital twin model to operate based on the first operation scheme and acquiring first virtual operation data generated in the operation process of the digital twin model; wherein the first virtual operating data characterizes operating performance of the digital twin model;
and the correcting module is used for correcting the digital twin model under the condition that the error between the first virtual operation data and the first actual operation data is larger than a first threshold value, so that the simulation degree of the digital twin model meets the simulation condition.
In some embodiments, the correction module is specifically configured to:
supplementarily acquiring second attribute information of the first device in the physical space;
and correcting the digital twin model based on the second attribute information so that the simulation degree of the corrected digital twin model meets the simulation condition.
In some embodiments, the apparatus further comprises:
the optimizing module is used for acquiring a target scheme by utilizing the digital twin model based on set target operation data; wherein the target operating data characterizes a target operating performance of the digital twin model, the target scheme being for controlling the digital twin model to operate and conforming the digital twin model to the target operating performance;
and the third control module is used for controlling the first equipment to operate based on the target scheme.
In some embodiments, the optimizing module is specifically configured to:
based on the target operation data, utilizing a mechanism model capable of representing the operation mechanism of the digital twin model to obtain at least one second operation scheme; wherein the mechanism model is a machine learning model;
controlling the digital twin model to operate based on each second operation scheme, and acquiring second virtual operation data generated in the operation process of the digital twin model;
and under the condition that the second virtual operation data accords with the target operation data, determining the corresponding second operation scheme as a first target scheme.
According to the data processing method, the digital twin model used for simulating the first equipment is built in the virtual space based on the first attribute information of the first equipment in the physical space, the first equipment and the digital twin model are controlled to operate based on the first operation scheme respectively, the first actual operation data generated in the operation process of the first equipment and the first virtual operation data generated in the operation process of the digital twin model are compared, and the digital twin model is corrected under the condition that the error between the first actual operation data and the first virtual operation data is larger than the first threshold value, so that the first equipment and the digital twin model can keep high consistency, and the accuracy of the simulation result of the digital twin model is improved.
Drawings
Fig. 1 is a flowchart of a first embodiment of a data processing method according to an embodiment of the present application;
FIG. 2 is a flow chart of a second embodiment of a data processing method according to an embodiment of the present application;
FIG. 3 is a block diagram of a data processing apparatus according to an embodiment of the present application;
fig. 4 is a block diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Various aspects and features of the present application are described herein with reference to the drawings.
It will be understood that various modifications may be made to the embodiments of the present application. Accordingly, the foregoing description should not be construed as limiting, but merely as exemplifications of embodiments. Those skilled in the art will envision other modifications within the scope and spirit of the application.
The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the application and, together with a general description of the application given above and the detailed description of the embodiments given below, serve to explain the principles of the application.
These and other characteristics of the present application will become apparent from the following description of preferred forms of embodiment, given as non-limiting examples, with reference to the attached drawings.
It should also be understood that, although the present application has been described with reference to some specific examples, a person of skill in the art shall certainly be able to achieve many other equivalent forms of application, having the characteristics as set forth in the claims and hence all coming within the field of protection defined thereby.
The above and other aspects, features and advantages of the present application will become more apparent in view of the following detailed description when taken in conjunction with the accompanying drawings.
Specific embodiments of the present application are described hereinafter with reference to the accompanying drawings; however, it is to be understood that the disclosed embodiments are merely exemplary of the application, which can be embodied in various forms. Well-known and/or repeated functions and constructions are not described in detail to avoid obscuring the application of unnecessary or unnecessary detail. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a basis for the claims and as a representative basis for teaching one skilled in the art to variously employ the present application in virtually any appropriately detailed structure.
The specification may use the phrases "in one embodiment," "in another embodiment," "in yet another embodiment," or "in other embodiments," which may each refer to one or more of the same or different embodiments in accordance with the application.
An embodiment of the present application provides a data processing method based on a digital twin model, and as shown in fig. 1, the data processing method according to the embodiment of the present application may specifically include the following steps:
s101, first attribute information of first equipment in a physical space is obtained.
Wherein the first apparatus may comprise a single apparatus, e.g., a single production processing apparatus. The first apparatus may also be a production line system composed of a plurality of apparatuses, for example, a chemical product production system composed of a plurality of apparatuses. In practical applications, the first device may be a plurality of types of devices, and the type of the first device is not limited herein. The first attribute information of the first device may include three-dimensional size information, process parameter information, action process information, and the like of the first device.
S102, constructing a digital twin model for simulating the first equipment in a virtual space based on the first attribute information.
The virtual space is a digital space for constructing the digital twin model, and the virtual space can be constructed by hardware and software of the electronic device together.
The digital twin model is a digital clone body of the first device constructed in the virtual space based on the first attribute information of the first device, and the digital twin model and the first device have the same three-dimensional size and the same operation mechanism and even trigger the same alarm or prompt due to the same event or state. The purpose is to make the digital twin model infinitely consistent with the first device to simulate the first device through the digital twin model.
Alternatively, the digital twin model may comprise a three-dimensional geometric model for simulating the first device, the three-dimensional geometric model having the same three-dimensional dimensions and operating mechanisms as the first device in physical space. The digital twin model may also include a data set module that may store historical operating schemes and historical operating data of the first device, the historical operating data characterizing historical operating performance of the first device, and a mechanism model. The mechanism model can characterize the operation mechanism of the digital twin model, and the mechanism model can be a machine learning model.
Specifically, while the first attribute information of the first device is acquired, the historical operation scheme and the historical operation data of the first device may also be acquired. And storing the historical operating scheme and the historical operating data in the data set module as data composition of the data set module. And training the mechanism model by using the historical operation scheme and the historical operation data. For example, the mechanism model may be trained by using historical operating data as input data and a historical operating scheme as output data, so that after the training of the mechanism model is completed, the operating data corresponding to the required operating performance is input, and the mechanism model can output the corresponding operating scheme.
Optionally, on the basis of constructing the digital twin model based on the first attribute information, the digital twin model may be controlled to operate based on a historical operation scheme, and the historical operation data is generated in the operation process of the digital twin model, so that the digital twin model is kept consistent with the first device. For example, the first device alarms in a specific operating state, and the control digital twin model alarms in the same operating state. Alternatively, the first device may produce a first production efficiency under a corresponding historical operating scenario, the first production efficiency also being produced when the digital twin model is controlled to operate based on the historical operating scenario.
S103, controlling the first equipment to operate based on a first operation scheme, and acquiring first actual operation data generated in the operation process of the first equipment; wherein the first actual operational data characterizes operational performance of the first device.
The first operation scheme may be a current operation scheme of the first device in the physical space, or may be a conventional operation scheme for controlling the operation of the first device in the corresponding technical field. Alternatively, in the case where a mechanical model is constructed, the first operation scheme may be an optimized operation scheme output by the mechanical model, for example, optimized operation data capable of characterizing the optimized operation performance may be input into the mechanical model, so that the mechanical model outputs one or more optimized operation schemes.
And controlling the first equipment to operate based on the first operation scheme, and continuously acquiring first actual operation data capable of representing the operation performance of the first equipment in the operation process of the first equipment. The first actual operation data may include, for example, production efficiency and product quality of the first device, and may further include aging performance of the first device, safety performance of the first device, and the like.
S104, controlling the digital twin model to operate based on the first operation scheme, and acquiring first virtual operation data generated in the operation process of the digital twin model; wherein the first virtual operating data characterizes operating performance of the digital twin model.
In order to maintain consistency between the first device and the digital twin model, in the process of controlling the first device to operate based on the first operation scheme, the digital twin model is continuously controlled to operate based on the same operation scheme, namely, based on the first operation scheme, and first virtual operation data generated in the process of operating the digital twin model is obtained. The first virtual operation data corresponds to the first actual operation data, and may include production efficiency and product quality of the digital twin model, aging performance of the digital twin model, safety performance of the digital twin model, and the like.
S105, under the condition that the error between the first virtual operation data and the first actual operation data is larger than a first threshold value, correcting the digital twin model to enable the simulation degree of the digital twin model to accord with simulation conditions.
And under the condition that the first virtual operation data and the first actual operation data are obtained, judging whether the error between the first virtual operation data and the first actual operation data is larger than a first threshold value or not. For example, an absolute value of a difference between the first virtual operation data and the first actual operation data is acquired, and the absolute value is compared with a first threshold value. The first threshold is an acceptable error range, and if the error between the first virtual operation data and the first actual operation data is smaller than the first threshold, the error between the digital twin model and the first device is within the acceptable error range, and the digital twin model does not need to be corrected. If the error between the first virtual operating data and the first actual operating data is greater than the first threshold value, indicating that the error between the digital twin model and the first device has reached an unacceptable degree, the correspondence between the digital twin model and the first device needs to be corrected so that the simulation degree of the digital twin model meets the simulation condition. That is, the digital twin model is made to conform to the first device to a preset target degree. The simulation condition can be judged through the three-dimensional sizes of the digital twin model and the first equipment, and also can be judged through the running data generated in the running process of the digital twin model and the first equipment.
According to the data processing method, the digital twin model used for simulating the first equipment is built in the virtual space based on the first attribute information of the first equipment in the physical space, the first equipment and the digital twin model are controlled to operate based on the first operation scheme respectively, the first actual operation data generated in the operation process of the first equipment and the first virtual operation data generated in the operation process of the digital twin model are compared, and the digital twin model is corrected under the condition that the error between the first actual operation data and the first virtual operation data is larger than the first threshold value, so that the first equipment and the digital twin model can keep high consistency, and the accuracy of the simulation result of the digital twin model is improved.
In particular implementations, the digital twin model may be corrected based on a variety of schemes when an error between the first virtual operating data and the first actual operating data is greater than a first threshold. For example, in a specific embodiment, the correcting the digital twin model to make the simulation degree of the digital twin model meet the simulation condition includes:
supplementarily acquiring second attribute information of the first device in the physical space;
and correcting the digital twin model based on the second attribute information so that the simulation degree of the corrected digital twin model meets the simulation condition.
The second attribute information is complementary to the first attribute information, and may be complementary to the first attribute information from the data sampling interval and the sampling density, for example, the three-dimensional size information is supplemented by increasing the sampling density of the three-dimensional size information, and for example, the process parameter information may be supplemented by reducing the sampling interval. The second attribute information may also supplement the first attribute information from the data type, for example, parameters of the production line such as temperature, pressure, flow rate, power consumption, etc. may be supplemented.
Under the condition that the second attribute information is acquired, the three-dimensional geometric model of the digital twin model can be corrected based on the second attribute information so as to correct the three-dimensional size and the operation mechanism of the digital twin model, so that the corrected digital twin model meets the simulation condition. For example, after the correction, the digital twin model may be controlled to operate based on the first operation scheme, another virtual operation data may be acquired and compared with the first actual operation data, and in the case that an error between the two is smaller than a first threshold value, it may be determined that the simulation degree of the digital twin model meets the simulation condition.
In another specific embodiment, the correcting the digital twin model to make the simulation degree of the digital twin model meet the simulation condition may include:
in the case that the first operation scheme is an operation scheme output by a mechanism model, the mechanism model may be trained based on the first operation scheme and first actual operation data to correct the operation mechanism of the digital twin model, so as to improve consistency of the operation mechanism of the digital twin model and the operation mechanism of the first device. In this way, the operation scheme output by the trained mechanism model can enable the first equipment to generate the set operation performance in the operation process, or enable the operation performance of the first equipment to be closer to the set operation performance.
As shown in conjunction with fig. 2, in some embodiments, the method further comprises:
s106, acquiring a target scheme by utilizing the digital twin model based on set target operation data; wherein the target operating data characterizes a target operating performance of the digital twin model, and the target scheme is used to control the digital twin model to operate and conform the digital twin model to the target operating performance.
And S107, controlling the first equipment to operate based on the target scheme.
The target operation data is a set debugging target or an optimization target and can represent at least one target operation performance of the digital twin model. Such as target capacity, target product quality, target safety factor, etc. In specific implementation, the digital twin model can be debugged or the operation process of the digital twin model can be optimized and adjusted based on the set target operation data, so that the simulation operation performance of the digital twin model conforms to the target operation performance. For example, the production efficiency of the digital twin model is made to reach a given target production efficiency, or the target safety factor of the digital twin model is made to reach a given target safety factor, or a specific event is made to occur or avoided in the digital twin model.
The target scheme is a simulation operation scheme for debugging the digital twin model or optimizing and adjusting the operation process of the digital twin model so that the simulation operation performance of the digital twin model conforms to the target operation performance. The target solution may include a full process control solution of the digital twin model, for example, when the digital twin model is a chemical production system model, the target solution may include control solutions of various links of various devices of the chemical production line. The target scheme may also include only the control scheme of one or more links of the digital twin model, for example, the operation control scheme of a certain device in the production line, or even the control scheme of a specific operation process of a certain device.
Since the digital twin model is used to simulate the first device, the digital twin model is controlled based on the target scheme, and the digital twin model can meet the target operation performance. On the basis, the first equipment in the physical space is controlled to operate based on the target scheme, and the first equipment generates an operation result which is the same as or similar to the digital twin model with a high probability, so that the operation data generated in the operation process of the first equipment accords with the target operation data, namely, the operation performance of the first equipment accords with the target operation performance.
Of course, it should be noted that the operation data generated during the operation of the first device described herein corresponds to the target operation data, and does not mean that the operation data completely reaches the target operation data, but should be understood to include approaching the target operation data or reaching the target operation data.
In some embodiments, the obtaining a target solution using the digital twin model based on the set target operating data includes:
based on the target operation data, utilizing a mechanism model capable of representing the operation mechanism of the first equipment to obtain at least one second operation scheme; wherein the mechanism model is a machine learning model;
controlling the digital twin model to operate based on each second operation scheme, and acquiring second virtual operation data generated in the operation process of the digital twin model;
and under the condition that the second virtual operation data accords with the target operation data, determining the corresponding second operation scheme as a first target scheme.
The mechanism model is a machine learning model, and the machine learning model may be a supervised learning model, an unsupervised learning model, a semi-supervised learning model or a reinforcement learning model, such as a neural network model, and the type of the machine learning model is not limited herein.
The mechanism model can be formed by training through the established model architecture. For example, after the historical operating scenario and the historical operating data are obtained, a training data set and a validation data set may be constructed based on the historical operating scenario and the historical operating data, the training data set and the validation data set each including input data and output data. The input data is formed from selected historical operating data and the output data is formed from a historical operating recipe.
When the mechanism model is constructed, firstly, a model architecture can be constructed, then, the model architecture is trained on the basis of input data and output data in a training data set, namely, historical operation data is used as input data, a historical operation scheme is used as output data, and the model architecture is trained. And then, inputting the input data in the verification data set into the trained model architecture, comparing the output data of the model architecture with the output data in the verification data set, and determining that the mechanism model training is completed if the output data meets the end condition.
When the target operation data is set, the target operation data may be input to the mechanism model as input data, and at least one second operation scenario output by the mechanism model may be acquired. Since the mechanism model is capable of characterizing the digital twin model and the operating mechanism of the first plant, target operating data is input into the mechanism model, which speculates on one or more second operating scenarios that may be consistent with the target operating data.
When the second operation scheme is obtained, the first device is not directly controlled based on the second operation scheme, the digital twin model can be controlled to operate based on each second operation scheme, and second virtual operation data generated in the process that the digital twin model operates based on each second operation scheme can be obtained. The second virtual operating data is capable of characterizing operating performance of the digital twin model during operation based on the second operating scenario. The second virtual operating data may then be compared to the target operating data to verify whether each second operating scenario enables the digital twin model to achieve the target operating performance. And if the second virtual operation data accords with the target operation data, determining the corresponding second operation scheme as the first target scheme.
In some embodiments, the method further comprises:
acquiring second actual operation data generated in the operation process of the first equipment based on the first target scheme;
training the mechanism model based on the second actual operating data and the first target scenario when an error between the second actual operating data and the target operating data is greater than a second threshold;
acquiring at least one third operation scheme by utilizing the trained mechanism model based on the target operation data;
controlling the digital twin model to operate based on each third operation scheme, and acquiring third virtual operation data generated in the operation process of the digital twin model;
determining the corresponding third operation scheme as a second target scheme under the condition that the third virtual operation data conforms to the target operation data;
and controlling the first equipment to operate based on the second target scheme, acquiring third actual operation data generated in the operation process of the first equipment, and iterating until the error between the third actual operation data and the target operation data is smaller than the second threshold value.
That is, when the first target scheme is obtained, the first device is controlled to operate based on the first target scheme, and second actual operation data generated in the operation process of the first device is obtained. And judging whether the error between the second actual operation data and the target operation data is larger than a second threshold value or not, wherein the second preset is used for representing that the second actual operation data does not accord with the target operation data. And training the mechanism model based on the second actual operation data and the first target operation scheme to correct the operation mechanism of the digital twin model under the condition that the error between the second actual operation data and the target operation data is larger than a second threshold value.
And then, inputting the target operation data into the trained mechanism model again, so that the trained mechanism model outputs at least one third operation scheme, namely a filial generation operation scheme. And controlling the digital twin model to operate based on each filial generation operation scheme, and selecting a second target scheme from the digital twin model. Controlling the first equipment to operate based on the second target scheme, acquiring third actual operation data generated in the operation process of the first equipment, judging whether the third actual operation data accords with the target operation data, and if the third actual operation data accords with the target operation data, indicating that a set optimization purpose is achieved; if the operation data do not accord with the target operation data, iteration is continued until a target scheme which can enable the operation data generated in the operation process of the first equipment to accord with the target operation data is obtained, namely the target scheme which can enable the operation performance of the first equipment to accord with the target operation performance is obtained.
In some embodiments, said controlling said first device to operate based on said target scheme comprises:
generating control instructions for controlling each operation process of the first equipment based on the target scheme, and forming an instruction set containing each control instruction;
sending the instruction set to an edge controller, wherein the instruction set is used for causing the edge controller to control the first device to operate based on the instruction set.
The target scheme is a control scheme capable of representing a technical process or an action process of the first equipment, and when the target scheme is obtained, a control instruction for controlling each operation process of the first equipment can be generated based on the target scheme. For example, control instructions that control various components or assemblies in the first device to perform startup, shutdown, or specific operations at specific time nodes. The control instruction may include, for example, time information indicating a time for executing the control instruction, absolute time information, or relative time information, and operation information indicating a specific operation performed by a certain component or assembly of the first device. Based on these control instructions, an instruction set is formed that can be recognized by the edge controller.
Then, the instruction set can be sent to an edge controller through a communication link, the edge controller is arranged on one side of the first device, and the edge controller controls the first device to operate based on the control instruction in the instruction set. By separating the optimizing equipment from the control equipment, the data processing capacity of the optimizing equipment and the timeliness of the control equipment can be considered.
Referring to fig. 3, an embodiment of the present application provides a data processing apparatus based on a digital twin model, including:
an obtaining module 201, configured to obtain first attribute information of a first device in a physical space;
a building module 202, configured to build a digital twin model for simulating the first device in a virtual space based on the first attribute information;
the first control module 203 is configured to control the first device to operate based on a first operation scheme, and obtain first actual operation data generated in an operation process of the first device; wherein the first actual operational data characterizes operational performance of the first device;
the second control module 204 is configured to control the digital twin model to operate based on the first operation scheme, and obtain first virtual operation data generated in the operation process of the digital twin model; wherein the first virtual operating data characterizes operating performance of the digital twin model;
a correcting module 205, configured to correct the digital twin model so that a simulation degree of the digital twin model meets a simulation condition when an error between the first virtual operation data and the first actual operation data is greater than a first threshold.
In some embodiments, the correction module 205 is specifically configured to:
supplementarily acquiring second attribute information of the first device in the physical space;
and correcting the digital twin model based on the second attribute information so that the simulation degree of the corrected digital twin model meets the simulation condition.
In some embodiments, the apparatus further comprises:
the optimizing module is used for acquiring a target scheme by utilizing the digital twin model based on set target operation data; wherein the target operating data characterizes a target operating performance of the digital twin model, the target scheme being for controlling the digital twin model to operate and conforming the digital twin model to the target operating performance;
and the third control module is used for controlling the first equipment to operate based on the target scheme.
In some embodiments, the optimizing module is specifically configured to:
based on the target operation data, utilizing a mechanism model capable of representing the operation mechanism of the digital twin model to obtain at least one second operation scheme; wherein the mechanism model is a machine learning model;
controlling the digital twin model to operate based on each second operation scheme, and acquiring second virtual operation data generated in the operation process of the digital twin model;
and under the condition that the second virtual operation data accords with the target operation data, determining the corresponding second operation scheme as a first target scheme.
In some embodiments, the optimizing module is further to:
acquiring second actual operation data generated in the operation process of the first equipment based on the first target scheme;
training the mechanism model based on the second actual operating data and the first target scenario when an error between the second actual operating data and the target operating data is greater than a second threshold;
acquiring at least one third operation scheme by utilizing the trained mechanism model based on the target operation data;
controlling the digital twin model to operate based on each third operation scheme, and acquiring third virtual operation data generated in the operation process of the digital twin model;
determining the corresponding third operation scheme as a second target scheme under the condition that the third virtual operation data conforms to the target operation data;
and controlling the first equipment to operate based on the second target scheme, acquiring third actual operation data generated in the operation process of the first equipment, and iterating until the error between the third actual operation data and the target operation data is smaller than the second threshold value.
In some embodiments, the second control module 204 is specifically configured to:
generating control instructions for controlling each operation process of the first equipment based on the target scheme, and forming an instruction set containing each control instruction;
sending the instruction set to an edge controller, wherein the instruction set is used for causing the edge controller to control the first device to operate based on the instruction set.
Referring to fig. 4, an electronic device is further provided in an embodiment of the present application, and includes at least a memory 301 and a processor 302, where the memory 301 stores a program, and the processor 302 implements the control method according to any of the above embodiments when executing the program on the memory 301.
It will be apparent to one skilled in the art that embodiments of the present application may be provided as methods, electronic devices, computer-readable storage media, or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media having computer-usable program code embodied in the medium. When implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium.
The processor may be a general purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a Programmable Logic Device (PLD), or a combination thereof. The PLD may be a Complex Programmable Logic Device (CPLD), a field-programmable gate array (FPGA), a General Array Logic (GAL), or any combination thereof. A general purpose processor may be a microprocessor or any conventional processor or the like.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
The readable storage medium may be a magnetic disk, an optical disk, a DVD, a USB, a Read Only Memory (ROM), a Random Access Memory (RAM), etc., and the specific form of the storage medium is not limited in this application.
The above embodiments are only exemplary embodiments of the present application, and are not intended to limit the present application, and the protection scope of the present application is defined by the claims. Various modifications and equivalents may be made by those skilled in the art within the spirit and scope of the present application and such modifications and equivalents should also be considered to be within the scope of the present application.
Claims (10)
1. A data processing method based on a digital twin model is characterized by comprising the following steps:
acquiring first attribute information of first equipment in a physical space;
constructing a digital twin model for simulating the first device in a virtual space based on the first attribute information;
controlling the first equipment to operate based on a first operation scheme, and acquiring first actual operation data generated in the operation process of the first equipment; wherein the first actual operational data characterizes operational performance of the first device;
controlling the digital twin model to operate based on the first operation scheme, and acquiring first virtual operation data generated in the operation process of the digital twin model; wherein the first virtual operating data characterizes operating performance of the digital twin model;
and under the condition that the error between the first virtual operation data and the first actual operation data is larger than a first threshold value, correcting the digital twin model so as to enable the simulation degree of the digital twin model to accord with the simulation condition.
2. The method of claim 1, wherein the correcting the digital twin model to make the degree of simulation of the digital twin model meet a simulation condition comprises:
supplementarily acquiring second attribute information of the first device in the physical space;
and correcting the digital twin model based on the second attribute information so that the simulation degree of the corrected digital twin model meets the simulation condition.
3. The method of claim 1, further comprising:
acquiring a target scheme by utilizing the digital twin model based on set target operation data; wherein the target operating data characterizes a target operating performance of the digital twin model, the target scheme being for controlling the digital twin model to operate and conforming the digital twin model to the target operating performance;
and controlling the first equipment to operate based on the target scheme.
4. The method of claim 3, wherein the obtaining a target solution using the digital twin model based on the set target operating data comprises:
based on the target operation data, utilizing a mechanism model capable of representing the operation mechanism of the digital twin model to obtain at least one second operation scheme; wherein the mechanism model is a machine learning model;
controlling the digital twin model to operate based on each second operation scheme, and acquiring second virtual operation data generated in the operation process of the digital twin model;
and under the condition that the second virtual operation data accords with the target operation data, determining the corresponding second operation scheme as a first target scheme.
5. The method of claim 4, further comprising:
acquiring second actual operation data generated in the operation process of the first equipment based on the first target scheme;
training the mechanism model based on the second actual operating data and the first target scenario when an error between the second actual operating data and the target operating data is greater than a second threshold;
acquiring at least one third operation scheme by utilizing the trained mechanism model based on the target operation data;
controlling the digital twin model to operate based on each third operation scheme, and acquiring third virtual operation data generated in the operation process of the digital twin model;
determining the corresponding third operation scheme as a second target scheme under the condition that the third virtual operation data conforms to the target operation data;
and controlling the first equipment to operate based on the second target scheme, acquiring third actual operation data generated in the operation process of the first equipment, and iterating until the error between the third actual operation data and the target operation data is smaller than the second threshold value.
6. The method of claim 3, wherein said controlling the operation of the first device based on the target solution comprises:
generating control instructions for controlling each operation process of the first equipment based on the target scheme, and forming an instruction set containing each control instruction;
sending the instruction set to an edge controller, wherein the instruction set is used for causing the edge controller to control the first device to operate based on the instruction set.
7. A data processing apparatus based on a digital twin model, comprising:
the device comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring first attribute information of first equipment in a physical space;
a building module, configured to build a digital twin model for simulating the first device in a virtual space based on the first attribute information;
the first control module is used for controlling the first equipment to operate based on a first operation scheme and acquiring first actual operation data generated in the operation process of the first equipment; wherein the first actual operational data characterizes operational performance of the first device;
the second control module is used for controlling the digital twin model to operate based on the first operation scheme and acquiring first virtual operation data generated in the operation process of the digital twin model; wherein the first virtual operating data characterizes operating performance of the digital twin model;
and the correcting module is used for correcting the digital twin model under the condition that the error between the first virtual operation data and the first actual operation data is larger than a first threshold value, so that the simulation degree of the digital twin model meets the simulation condition.
8. The apparatus of claim 7, wherein the correction module is specifically configured to:
supplementarily acquiring second attribute information of the first device in the physical space;
and correcting the digital twin model based on the second attribute information so that the simulation degree of the corrected digital twin model meets the simulation condition.
9. The apparatus of claim 7, further comprising:
the optimizing module is used for acquiring a target scheme by utilizing the digital twin model based on set target operation data; wherein the target operating data characterizes a target operating performance of the digital twin model, the target scheme being for controlling the digital twin model to operate and conforming the digital twin model to the target operating performance;
and the third control module is used for controlling the first equipment to operate based on the target scheme.
10. The apparatus of claim 9, wherein the optimizing module is specifically configured to:
based on the target operation data, utilizing a mechanism model capable of representing the operation mechanism of the digital twin model to obtain at least one second operation scheme; wherein the mechanism model is a machine learning model;
controlling the digital twin model to operate based on each second operation scheme, and acquiring second virtual operation data generated in the operation process of the digital twin model;
and under the condition that the second virtual operation data accords with the target operation data, determining the corresponding second operation scheme as a first target scheme.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111427677.XA CN113868898A (en) | 2021-11-29 | 2021-11-29 | Data processing method and device based on digital twin model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111427677.XA CN113868898A (en) | 2021-11-29 | 2021-11-29 | Data processing method and device based on digital twin model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113868898A true CN113868898A (en) | 2021-12-31 |
Family
ID=78985379
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111427677.XA Pending CN113868898A (en) | 2021-11-29 | 2021-11-29 | Data processing method and device based on digital twin model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113868898A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114707428A (en) * | 2022-06-01 | 2022-07-05 | 中科航迈数控软件(深圳)有限公司 | Method, device, terminal and storage medium for simulating unobservable links of numerical control machine tool |
| CN114814759A (en) * | 2022-06-28 | 2022-07-29 | 湖南师范大学 | Airborne radar signal processing and data storage method and component based on digital twinning |
| CN114841021A (en) * | 2022-07-04 | 2022-08-02 | 北京航空航天大学杭州创新研究院 | Method and device for correcting digital twin model, electronic device and storage medium |
| CN115164378A (en) * | 2022-06-09 | 2022-10-11 | 中国电子工程设计院有限公司 | Fresh air handling unit regulation and control method based on digital twins and related device |
| CN116088325A (en) * | 2022-12-05 | 2023-05-09 | 广州视声智能股份有限公司 | Digital twinning-based household equipment control method and device and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111461338A (en) * | 2020-03-06 | 2020-07-28 | 北京仿真中心 | Intelligent system updating method and device based on digital twin |
| US20200326692A1 (en) * | 2019-04-10 | 2020-10-15 | Guangdong University Of Technology | Parallel control method based on multi-period differential sampling and digital twinning technologies |
| CN112417619A (en) * | 2020-11-23 | 2021-02-26 | 江苏大学 | Pump unit optimal operation adjusting system and method based on digital twinning |
| CN112487584A (en) * | 2020-12-03 | 2021-03-12 | 天津工业大学 | Dynamics-based rolling bearing digital twin modeling method |
| CN112906299A (en) * | 2021-02-05 | 2021-06-04 | 北京交通大学 | Data calculation method and system for digital twin simulation of urban rail power supply system |
| CN113495577A (en) * | 2021-09-07 | 2021-10-12 | 南京航空航天大学 | Unmanned aerial vehicle cluster sensor model correction method for digital twin simulation |
-
2021
- 2021-11-29 CN CN202111427677.XA patent/CN113868898A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200326692A1 (en) * | 2019-04-10 | 2020-10-15 | Guangdong University Of Technology | Parallel control method based on multi-period differential sampling and digital twinning technologies |
| CN111461338A (en) * | 2020-03-06 | 2020-07-28 | 北京仿真中心 | Intelligent system updating method and device based on digital twin |
| CN112417619A (en) * | 2020-11-23 | 2021-02-26 | 江苏大学 | Pump unit optimal operation adjusting system and method based on digital twinning |
| CN112487584A (en) * | 2020-12-03 | 2021-03-12 | 天津工业大学 | Dynamics-based rolling bearing digital twin modeling method |
| CN112906299A (en) * | 2021-02-05 | 2021-06-04 | 北京交通大学 | Data calculation method and system for digital twin simulation of urban rail power supply system |
| CN113495577A (en) * | 2021-09-07 | 2021-10-12 | 南京航空航天大学 | Unmanned aerial vehicle cluster sensor model correction method for digital twin simulation |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114707428A (en) * | 2022-06-01 | 2022-07-05 | 中科航迈数控软件(深圳)有限公司 | Method, device, terminal and storage medium for simulating unobservable links of numerical control machine tool |
| CN115164378A (en) * | 2022-06-09 | 2022-10-11 | 中国电子工程设计院有限公司 | Fresh air handling unit regulation and control method based on digital twins and related device |
| CN114814759A (en) * | 2022-06-28 | 2022-07-29 | 湖南师范大学 | Airborne radar signal processing and data storage method and component based on digital twinning |
| CN114814759B (en) * | 2022-06-28 | 2022-10-28 | 湖南师范大学 | Airborne radar signal processing and data storage method and component based on digital twinning |
| CN114841021A (en) * | 2022-07-04 | 2022-08-02 | 北京航空航天大学杭州创新研究院 | Method and device for correcting digital twin model, electronic device and storage medium |
| CN116088325A (en) * | 2022-12-05 | 2023-05-09 | 广州视声智能股份有限公司 | Digital twinning-based household equipment control method and device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113868898A (en) | Data processing method and device based on digital twin model | |
| CN113836755A (en) | Control method and device based on digital twin model | |
| CN108108532A (en) | With the method for particle cluster algorithm optimization power electronic circuit | |
| CN113591954B (en) | Filling method of missing time sequence data in industrial system | |
| CN115600140A (en) | Fan variable pitch system fault identification method and system based on multi-source data fusion | |
| Aflaki et al. | Automated fine tuning of probabilistic self-stabilizing algorithms | |
| US11573542B2 (en) | Method and apparatus for adjusting process control prediction model and process controller | |
| EP3195438B1 (en) | System, method and apparatus for determining parameter settings for a power generation system and a tangible computer readable medium | |
| US20230033495A1 (en) | Evaluation method for training data, program, generation method for training data, generation method for trained model, and evaluation system for training data | |
| CN117195454A (en) | Method and device for constructing digital twin body of power grid, electronic equipment and storage medium | |
| CN113887989B (en) | Power system reliability evaluation method, device, computer equipment and storage medium | |
| CN112531725B (en) | Method and system for identifying parameters of static var generator | |
| US11556760B2 (en) | Learning-based data processing system and model update method | |
| CN113221390A (en) | Training method and device for scheduling model | |
| CN113743571A (en) | Data processing method, electronic device and storage medium | |
| CN116345544B (en) | Genetic algorithm-based power system safety and stability control strategy generation method, device and system and storage medium | |
| CN112488319A (en) | Parameter adjusting method and system with self-adaptive configuration generator | |
| KR20130071734A (en) | Error correctable intelligence system and method thereof | |
| CN117349605A (en) | New energy unit synchronous phasor measurement abnormal data restoration method | |
| CN113591275B (en) | method, device and equipment for calibrating model | |
| JP2020187616A (en) | Plant monitoring model creation device, plant monitoring model creation method, and plant monitoring model creation program | |
| KR102222072B1 (en) | Apparatus for Processing Data based on Learning and Method for Update of Model | |
| CN111723827B (en) | Industrial process monitoring method, device and equipment based on kernel dictionary learning | |
| CN117057255B (en) | Pre-training model acquisition method for online synchronization of digital twin model | |
| CN115688352A (en) | High voltage generator control method and system based on machine learning, electronic device and computer storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211231 |
|
| RJ01 | Rejection of invention patent application after publication |