A management method for digital twin feature layers

Abstract

The present invention discloses a management method for a digital twin feature layer, which relates to the field of digital twin technology. The method comprises: searching and classifying the power equipment operation feature data stream according to the equipment operation attribute classifier, and then encoding the classified equipment operation feature attribute information based on the feature layer encoding rule to obtain the equipment operation attribute feature code information, thereby integrating the power equipment operation feature data stream, and using the digital twin technology to simulate and model the integrated equipment operation feature layer data stream to generate a power equipment operation twin model; updating and learning the power equipment operation twin model through the equipment cycle change characteristics to obtain the power equipment operation optimization twin model, and then using it to control the power equipment operation. The technical effect of realizing the optimization of digital twin model modeling through the efficient management of the digital twin feature layer, improving the accuracy of power equipment control, and then improving the modeling efficiency is achieved.

Description

Technical Field

[0001] The present invention relates to the field of digital twin technology, and in particular to a method for managing a digital twin feature layer. Background Art

[0002] With the rapid development of the power industry, traditional power equipment monitoring and fault diagnosis methods can no longer meet the needs of modern complex power systems. Digital twin technology provides new solutions for real-time monitoring, fault prediction and optimized operation of power equipment. However, the existing digital twin model has low control accuracy and low modeling efficiency. Summary of the invention

[0003] The present application solves the technical problems of low control accuracy and low modeling efficiency of digital twin models in the prior art by providing a management method for digital twin feature layers, thereby achieving the technical effect of optimizing digital twin model modeling through efficient management of digital twin feature layers, improving the control accuracy of power equipment, and thereby improving modeling efficiency.

[0004] In view of the above problems, the present invention provides a method for managing digital twin feature layers.

[0005] In the first aspect, the present application provides a management method for a digital twin feature layer, the method comprising: acquiring an electric power equipment operation feature data stream through a sensor group, the electric power equipment operation feature data stream comprising an equipment operation status data stream and electric power equipment attribute information; constructing an equipment operation attribute classifier, retrieving and classifying the electric power equipment operation feature data stream according to the equipment operation attribute classifier, and obtaining the equipment operation feature attribute information; acquiring a feature layer coding rule, encoding the equipment operation feature attribute information based on the feature layer coding rule, and obtaining equipment operation attribute feature code information; integrating the electric power equipment operation feature data stream according to the equipment operation attribute feature code information, and obtaining an equipment operation feature layer data stream; using digital twin technology to simulate and model the equipment operation feature layer data stream, and generate an electric power equipment operation twin model; updating and learning the electric power equipment operation twin model through equipment cycle change characteristics, and obtaining an electric power equipment operation optimization twin model, and performing electric power equipment operation management and control based on the electric power equipment operation optimization twin model.

[0006] On the other hand, the present application also provides a management system for a digital twin feature layer, the system comprising: an operation feature data stream acquisition module, which is used to acquire the operation feature data stream of the power equipment through a sensor group, and the operation feature data stream of the power equipment includes an equipment operation status data stream and power equipment attribute information; a data stream retrieval and classification module, which is used to construct an equipment operation attribute classifier, retrieve and classify the operation feature data stream of the power equipment according to the equipment operation attribute classifier, and obtain the equipment operation feature attribute information; a feature attribute information encoding module, which is used to acquire a feature layer encoding rule, encode the equipment operation feature attribute information based on the feature layer encoding rule, and obtain the equipment operation attribute feature code information; a data stream integration module, which is used to integrate the power equipment operation feature data stream according to the equipment operation attribute feature code information, and obtain the equipment operation feature layer data stream; a simulation modeling module, which is used to simulate and model the equipment operation feature layer data stream using digital twin technology, and generate an electric equipment operation twin model; an electric equipment operation control module, which is used to update and learn the electric equipment operation twin model through equipment cycle change characteristics, obtain an electric equipment operation optimization twin model, and perform power equipment operation control based on the electric equipment operation optimization twin model.

[0007] In a third aspect, the present application provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps of any one of the above methods.

[0008] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps in any one of the above-mentioned methods when executed by a processor.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] The power equipment operation characteristic data stream is retrieved and classified according to the equipment operation attribute classifier, and then the classified equipment operation characteristic attribute information is encoded based on the feature layer encoding rules to obtain the equipment operation attribute characteristic code information, so as to integrate the power equipment operation characteristic data stream, and use the digital twin technology to simulate and model the integrated equipment operation characteristic layer data stream to generate a power equipment operation twin model; the power equipment operation twin model is updated and learned through the equipment cycle change characteristics to obtain the power equipment operation optimization twin model, and then the technical solution for power equipment operation control based on the power equipment operation optimization twin model is achieved. Then, the technical effect of realizing digital twin model modeling optimization through efficient management of digital twin feature layers, improving the accuracy of power equipment control, and then improving modeling efficiency is achieved.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A flowchart of a method for managing a digital twin feature layer for this application;

[0013] Figure 2 A structural diagram of a management system for a digital twin feature layer for this application;

[0014] Figure 3 This is a schematic diagram of the structure of an exemplary electronic device of the present application.

[0015] Explanation of the reference numerals: operation characteristic data stream acquisition module 11, data stream retrieval classification module 12, characteristic attribute information encoding module 13, data stream integration module 14, simulation modeling module 15, power equipment operation control module 16, bus 1110, processor 1120, transceiver 1130, bus interface 1140, memory 1150, operating system 1151, application 1152 and user interface 1160. DETAILED DESCRIPTION

[0016] In the description of the present application, those skilled in the art should know that the present application can be implemented as a method, an apparatus, an electronic device, and a computer-readable storage medium. Therefore, the present application can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), a combination of hardware and software. In addition, in some embodiments, the present application can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage medium contains computer program code.

[0017] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disc read-only memories, optical storage devices, magnetic storage devices, or any combination of the above. In the present application, computer-readable storage media can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.

[0018] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws.

[0019] The present application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0020] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer-readable program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified by the boxes in the flowchart and / or block diagram.

[0021] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product including functions / operations specified in the blocks in the flowchart and / or block diagram.

[0022] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0023] The present application is described below in conjunction with the drawings in the present application.

[0024] Embodiment 1

[0025] like Figure 1As shown, the present application provides a method for managing a digital twin feature layer, the method comprising:

[0026] Step S1: acquiring a power equipment operation characteristic data stream through a sensor group, wherein the power equipment operation characteristic data stream includes a device operation status data stream and power equipment attribute information;

[0027] Specifically, in order to achieve the modeling accuracy of the digital twin model of power equipment, the equipment data is collected through the sensor group deployed on the power equipment of the power grid, wherein the sensor group includes voltage sensors, current sensors, temperature sensors, pressure sensors, etc. The power equipment operation characteristic data stream is acquired through real-time monitoring of the sensor group. The power equipment operation characteristic data stream is the operation data stream of each attribute type of power equipment, including the equipment operation status data stream of each time period measured by the sensor group; and power equipment attribute information, wherein the power equipment attribute information is the relevant production application attribute information of each type of power equipment, including equipment type, model, application function, spatial location, etc. By real-time monitoring of power equipment operation data, the comprehensiveness of data acquisition is improved, providing a data basis for subsequent digital twin modeling, thereby improving modeling accuracy.

[0028] Step S2: constructing an equipment operation attribute classifier, searching and classifying the power equipment operation characteristic data stream according to the equipment operation attribute classifier, and obtaining equipment operation characteristic attribute information;

[0029] Furthermore, the steps of constructing the device operation attribute classifier in this application also include:

[0030] Determine a device operation characteristic attribute set and a device characteristic attribute set according to the device operation status data stream and the power device attribute information;

[0031] Performing principal component analysis on the equipment operation feature attribute set and the equipment feature attribute set to obtain an equipment dimension reduction data feature set, wherein the equipment dimension reduction data feature set includes operation attribute features, operation space-time features, and equipment attribute features;

[0032] Performing information theory coding operations on the operation attribute features, operation space-time features and equipment attribute features respectively to obtain classifier feature node information;

[0033] Based on the classifier feature node information, the device operation attribute classifier is constructed.

[0034] Furthermore, the step of obtaining the feature node information of the classifier also includes:

[0035] Extracting knowledge from the operation attribute features, operation spatiotemporal features, and equipment attribute features respectively to obtain an equipment operation attribute entity set;

[0036] Filling each attribute entity in the device operation attribute entity set with content to obtain a device operation attribute entity content set;

[0037] An information theory coding operation is performed based on the device operation attribute entity content set to obtain the classifier feature node information.

[0038] Specifically, in order to improve the quality of data modeling, the collected power equipment data is preprocessed with feature layers. The digital twin feature layer refers to a layer of data in the digital twin system, which reflects a form of expression of the physical object in the digital space and is the basis for realizing virtual-real mapping, real-time synchronization, symbiotic evolution and closed-loop optimization. The digital twin feature layer contains a variety of information such as the appearance, performance, location, and anomalies of the physical object. Through the management and application of the feature layer, the digital twin model can more accurately monitor and predict the state and behavior of the power equipment and improve the reliability of the equipment. First, according to the equipment operation status data stream, the equipment operation feature attribute set is determined. The equipment operation feature attribute set corresponds to all data source types in the equipment operation status data stream, including voltage operation feature attributes, current operation feature attributes, temperature operation feature attributes, pressure operation feature attributes, etc. At the same time, according to the power equipment attribute information, the equipment feature attribute set is determined. The equipment feature attribute set corresponds to all attribute types in the power equipment attribute information, including equipment type feature attributes, model feature attributes, application function feature attributes, etc.

[0039] Since there are many types of data feature attributes, the data processing efficiency is reduced. Therefore, principal component analysis is performed on the equipment operation feature attribute set and the equipment feature attribute set. Principal component analysis is the most commonly used linear dimensionality reduction method. It maps high-dimensional data to low-dimensional space through a certain linear projection, and expects the data information volume to be the largest (maximum variance) on the projected dimension, that is, the original feature attributes are projected onto the dimension with the largest projection information volume as much as possible, so that the information loss after dimensionality reduction is minimized. The principal component analysis dimensionality reduction process is used to obtain a critical equipment dimensionality reduction data feature set, which includes the equipment operation feature attribute characteristics after the dimensionality reduction of the equipment operation feature attribute set; the operation spatiotemporal characteristics, which are the spatial location information of the power equipment and the collection time information of the equipment operation data; and the equipment attribute characteristics after the dimensionality reduction of the equipment feature attribute set.

[0040] The operation attribute characteristics, operation spatiotemporal characteristics and equipment attribute characteristics are respectively subjected to information theory coding operations. First, knowledge is extracted from the operation attribute characteristics, operation spatiotemporal characteristics and equipment attribute characteristics, that is, the classification of each characteristic is determined by the professional classification standard of power equipment data, and the corresponding equipment operation attribute entity set is obtained. Exemplarily, the voltage attribute characteristics in the operation attribute characteristics can be classified into low voltage, medium voltage, high voltage, ultra-high voltage, etc. according to the level classification of power operation standards, and each attribute characteristic classification class is regarded as an attribute entity. Then, each attribute entity in the equipment operation attribute entity set is filled with content, that is, the detailed content of each attribute entity is classified and filled. Exemplarily, 240V and below belong to low voltage entity content, and 10KV and below belong to medium voltage entity content, thereby obtaining a set of equipment operation attribute entity content filled with specific category content.

[0041] Based on the set of entity content of the equipment operation attribute, information theory coding operation is performed. The set of entity content of the equipment operation attribute can be used as the internal node of the classifier, and each entity content can be used as a node to obtain the characteristic node information of the classifier. The information entropy of the characteristic node information of the classifier is calculated by the Shannon formula in information theory coding, and the features with the smallest entropy value can be classified first, and then the features of each node are classified in order from small to large entropy values, so as to realize the recursive construction of the classifier, so as to form the equipment operation attribute classifier. The equipment operation attribute classifier is similar to a tree structure and is used to quickly classify the attributes of the equipment operation data stream. And according to the equipment operation attribute classifier, the power equipment operation characteristic data stream is retrieved and classified, and the equipment operation characteristic attribute information corresponding to each power equipment operation characteristic data stream is obtained, so as to realize the labeling of the data stream characteristic attribute. Improve the accuracy and comprehensiveness of the classification of equipment operation characteristic attributes, thereby improving the efficiency of data stream processing.

[0042] Step S3: Acquire a feature layer coding rule, and encode the device operation feature attribute information based on the feature layer coding rule to obtain device operation attribute feature code information;

[0043] Furthermore, the step of obtaining the feature layer coding rule in this application also includes:

[0044] Determine a layer coding content system based on the device dimension reduction data feature set, the device operation attribute entity set, and the device operation attribute entity content set;

[0045] Dividing the coding level according to the layer coding content system to obtain feature layer coding level information;

[0046] Based on the layer coding content system and the feature layer coding level information, setting a layer feature code identification criterion;

[0047] The feature layer encoding rule is determined based on the feature layer encoding level information and the layer feature code identification criterion.

[0048] Specifically, in order to realize the rapid integration of data streams, the layer coding content system is determined based on the device dimension reduction data feature set, the device operation attribute entity set, and the device operation attribute entity content set. The layer coding content system is the feature layer coding content, and the above-mentioned device dimension reduction data feature set, device operation attribute entity set, and device operation attribute entity content set need to be content coded. The coding level is divided according to the layer coding content system, that is, the content in the layer coding content system is determined according to the classifier level, and then the corresponding feature layer coding level information is obtained. The order of the feature layer coding level information is the device dimension reduction data feature set, the device operation attribute entity set, and the device operation attribute entity content set.

[0049] Based on the layer coding content system and the feature layer coding level information, set the layer feature code identification criteria, which are the number of feature code identification digits set according to the layer coding content system and the feature layer coding level, that is, the number of digits used to identify the content of each layer coding in hierarchical order; and feature code identification symbols, that is, symbols used to identify the content of each layer coding in hierarchical order, such as numbers, letters, etc., which can be selected and set at will. Based on the feature layer coding level information and the layer feature code identification criteria, determine the feature layer coding rules, which are the coding basis for the feature layer data, including the coding content level order and coding identification. And encode the device operation feature attribute information based on the feature layer coding rules to obtain the device operation attribute feature code information corresponding to each feature attribute. Realize fast coding and logical identification of feature attributes, thereby improving data processing efficiency.

[0050] Step S4: integrating the power equipment operation characteristic data stream according to the equipment operation attribute characteristic code information to obtain the equipment operation characteristic layer data stream;

[0051] Specifically, the power equipment operation characteristic data stream is integrated according to the equipment operation attribute characteristic code information, that is, the data streams of the same equipment operation attribute characteristic code are integrated into one category, and the integrated equipment operation characteristic layer data stream is obtained. Through the efficient management of the digital twin feature layer, data can be quickly and accurately integrated, providing a data foundation for subsequent digital twin modeling, thereby improving modeling accuracy and efficiency.

[0052] Step S5: using digital twin technology to simulate and model the data stream of the equipment operation feature layer to generate a power equipment operation twin model;

[0053] Furthermore, the generation of the power equipment operation twin model, the application step also includes:

[0054] Extracting entity elements from the device operation feature layer data stream to obtain the device operation entity layer data stream;

[0055] Simulate the data flow of the equipment operation entity layer according to the preset modeling granularity level to generate a power equipment topology network source model;

[0056] Acquire power equipment function factor information, classify the equipment operation feature layer data stream according to the power equipment function factor information, and acquire an operation factor layer sample set;

[0057] The operation factor layer sample set is trained to obtain a set of equipment operation factor function models, and the power equipment topology network source model and the set of equipment operation factor function models are integrated using digital twin technology to generate the power equipment operation twin model.

[0058] Furthermore, the step of obtaining the functional model set of equipment operation factors in this application further includes:

[0059] Get the long short-term memory network model;

[0060] Using the long short-term memory network model, the sample sets of the operation factor layers are trained respectively to determine the model weights and model biases;

[0061] The model weights and model biases are iteratively trained through a back-propagation algorithm until a preset model accuracy rate is reached, thereby obtaining a set of functional models of the equipment operation factors.

[0062] Specifically, the digital twin technology is used to simulate and model the data stream of the equipment operation feature layer. Specifically, the entity elements of the equipment operation feature layer data stream are first extracted, that is, the device attribute characteristics and the device spatial location characteristics and other factor data are extracted, and the device operation entity layer data stream corresponding to the entity element mapping is obtained, so as to model the real physical entity of the power equipment. The modeling granularity level is set by yourself, that is, the accuracy level used in modeling. The finer the modeling granularity, the higher the model accuracy, and the amount of calculation will also increase. Therefore, the modeling granularity can be set according to application requirements. The equipment operation entity layer data stream is simulated according to the preset modeling granularity level to generate a power equipment topology network source model. The power equipment topology network source model is an abstract simulation three-dimensional model of the power equipment. It is the basic architecture model of the digital twin model, which is used to describe and display the topological relationship of the equipment entity resources.

[0063] At the same time, the functional factor information of the power equipment is obtained. The functional factor information of the power equipment is the application function required by the digital twin model, such as the functional factor of equipment operation fault identification, the functional factor of operation status prediction, the functional factor of energy consumption analysis, etc., which can be configured and determined by itself. The data stream of the equipment operation feature layer is classified by the functional factor information of the power equipment, that is, the data stream is classified according to the required functional factors, and the data streams of the same factors are divided into one category, so as to obtain the classified operation factor layer sample set as the functional model training sample. The operation factor layer sample set is trained, specifically, firstly obtaining a long short-term memory network model as the functional model training network, which is a recurrent neural network with stronger generalization ability and better effect in processing time series data. The operation factor layer sample set is trained respectively by using the long short-term memory network model to determine the model weight and model bias. The model weight and model bias are model parameters, which define the connection mode and strength of each layer in the long short-term memory neural network. These parameters are continuously updated during the training process.

[0064] The model weights and model biases are iteratively trained by the back propagation algorithm, that is, the model weights and model biases are iteratively updated according to the gradient information of the loss function by the back propagation algorithm. In each training iteration, the model calculates the output result according to the current input data and weights, biases and other parameters, and then compares it with the true value to calculate the value of the loss function. Then, the gradient information is calculated by the back propagation algorithm, and the parameters such as the model weight matrix and the bias term are updated, so that the loss function value gradually decreases, so that the output result of the model is closer to the true value, until the preset model accuracy is reached, and the final trained equipment operation factor function model set is obtained, which is used to realize the application functions such as power equipment operation fault identification, operation status prediction, and energy consumption analysis. Then, the power equipment topology network source model and the equipment operation factor function model set are embedded by using digital twin technology, and the power equipment operation twin model is generated by merging. Real-time monitoring and accurate prediction of power equipment are realized through digital twin technology, which improves the safety and reliability of equipment.

[0065] Step S6: Update and learn the power equipment operation twin model through the equipment periodic change characteristics to obtain the power equipment operation optimization twin model, and perform power equipment operation management and control based on the power equipment operation optimization twin model.

[0066] Furthermore, the steps of obtaining the power equipment operation optimization twin model in this application also include:

[0067] Inputting the equipment periodic variation characteristics into the power equipment operation twin model for prediction, and outputting the power equipment prediction operation data;

[0068] Obtaining equipment operation loss data by performing data loss analysis on the predicted operation data of the electric power equipment;

[0069] The equipment operation loss data is trained based on the power equipment operation twin model to obtain the power equipment operation optimization twin model.

[0070] Specifically, the power equipment operation twin model is updated and learned through the equipment cycle change characteristics, wherein the equipment cycle change characteristics are the operation data update cycle of the power equipment, which can be set according to the actual working demand experience of the equipment. The equipment cycle change characteristics are input into the power equipment operation twin model for prediction, and the power equipment predicted operation data corresponding to the equipment cycle change characteristics are output. The power equipment predicted operation data is the corresponding predicted business data obtained by training the power equipment operation twin model based on the equipment cycle change characteristics, including equipment operation fault prediction data, operation status prediction data, energy consumption analysis prediction data, etc.

[0071] Therefore, by introducing the loss function, the loss analysis of the predicted operation data of the power equipment is completed, and then the equipment operation loss data is obtained, wherein the equipment operation loss data is the loss data representing the relevant data knowledge of the power equipment operation twin model for the periodic change characteristics of the equipment. Then, based on the equipment operation loss data, the update training and learning of the power equipment operation twin model is completed. Since the power equipment operation twin model is obtained by connecting multiple neurons to form a neural network, the power equipment operation optimization twin model retains the basic functions of the power equipment operation twin model through the training of loss data, and maintains the performance of the model being continuously updated. And based on the power equipment operation optimization twin model, the power equipment operation control is carried out to achieve accurate monitoring, prediction and optimization of the power equipment, improve the update performance of the power equipment operation optimization twin model, and thus ensure the technical effect of the accuracy of power equipment operation control.

[0072] In summary, the management method of a digital twin feature layer provided by this application has the following technical effects:

[0073] The power equipment operation characteristic data stream is retrieved and classified according to the equipment operation attribute classifier, and then the classified equipment operation characteristic attribute information is encoded based on the feature layer encoding rules to obtain the equipment operation attribute characteristic code information, so as to integrate the power equipment operation characteristic data stream, and use the digital twin technology to simulate and model the integrated equipment operation characteristic layer data stream to generate a power equipment operation twin model; the power equipment operation twin model is updated and learned through the equipment cycle change characteristics to obtain the power equipment operation optimization twin model, and then the technical solution for power equipment operation control based on the power equipment operation optimization twin model is achieved. Then, the technical effect of realizing digital twin model modeling optimization through efficient management of digital twin feature layers, improving the accuracy of power equipment control, and then improving modeling efficiency is achieved.

[0074] Embodiment 2

[0075] Based on the same inventive concept as the management method of a digital twin feature layer in the aforementioned embodiment, the present invention also provides a management system for a digital twin feature layer, such as Figure 2 As shown, the system comprises:

[0076] An operation characteristic data stream acquisition module 11 is used to acquire an operation characteristic data stream of an electric power device through a sensor group, wherein the operation characteristic data stream of the electric power device includes an equipment operation status data stream and electric power device attribute information;

[0077] The data stream retrieval classification module 12 is used to construct an equipment operation attribute classifier, retrieve and classify the power equipment operation characteristic data stream according to the equipment operation attribute classifier, and obtain equipment operation characteristic attribute information;

[0078] The characteristic attribute information encoding module 13 is used to obtain a characteristic layer encoding rule, and encode the device operation characteristic attribute information based on the characteristic layer encoding rule to obtain the device operation attribute characteristic code information;

[0079] The data stream integration module 14 is used to integrate the power equipment operation characteristic data stream according to the equipment operation attribute characteristic code information to obtain the equipment operation characteristic layer data stream;

[0080] A simulation modeling module 15 is used to simulate and model the data stream of the equipment operation feature layer using digital twin technology to generate a power equipment operation twin model;

[0081] The power equipment operation control module 16 is used to update and learn the power equipment operation twin model through the equipment periodic change characteristics, obtain the power equipment operation optimization twin model, and perform power equipment operation control based on the power equipment operation optimization twin model.

[0082] Furthermore, the system also includes:

[0083] A characteristic attribute determination unit, used to determine a device operation characteristic attribute set and a device characteristic attribute set according to the device operation status data stream and the power device attribute information;

[0084] A principal component analysis unit, used to perform principal component analysis on the equipment operation feature attribute set and the equipment feature attribute set to obtain an equipment dimension reduction data feature set, wherein the equipment dimension reduction data feature set includes an operation attribute feature, an operation space-time feature, and an equipment attribute feature;

[0085] A feature node obtaining unit, used to perform information theory coding operations on the operation attribute features, operation space-time features and device attribute features respectively to obtain classifier feature node information;

[0086] The attribute classifier construction unit is used to construct the device operation attribute classifier based on the classifier feature node information.

[0087] Furthermore, the system also includes:

[0088] A knowledge extraction unit, used to extract knowledge from the operation attribute characteristics, operation space-time characteristics and equipment attribute characteristics respectively, and obtain an equipment operation attribute entity set;

[0089] An entity content filling unit, used to fill the content of each attribute entity in the device operation attribute entity set respectively, to obtain a device operation attribute entity content set;

[0090] The information theory coding operation unit is used to perform information theory coding operation based on the device operation attribute entity content set to obtain the classifier feature node information.

[0091] Furthermore, the system also includes:

[0092] A coding content system determining unit, configured to determine a layer coding content system based on the device dimension reduction data feature set, the device operation attribute entity set, and the device operation attribute entity content set;

[0093] A coding level division unit, used for performing coding level division according to the layer coding content system to obtain feature layer coding level information;

[0094] An identification criterion setting unit, used to set a layer feature code identification criterion based on the layer coding content system and the feature layer coding level information;

[0095] The encoding rule determination unit is used to determine the feature layer encoding rule based on the feature layer encoding level information and the layer feature code identification criterion.

[0096] Furthermore, the system also includes:

[0097] An entity element extraction unit, used to extract entity elements from the device operation feature layer data stream to obtain the device operation entity layer data stream;

[0098] A network source model generation unit is used to simulate the data flow of the device operation entity layer according to a preset modeling granularity level to generate a power equipment topology network source model;

[0099] A data stream classification unit, used to obtain power equipment function factor information, classify the equipment operation feature layer data stream according to the power equipment function factor information, and obtain an operation factor layer sample set;

[0100] The twin model generation unit is used to train the operation factor layer sample set to obtain the equipment operation factor function model set, and use the digital twin technology to integrate the power equipment topology network source model and the equipment operation factor function model set to generate the power equipment operation twin model.

[0101] Furthermore, the system also includes:

[0102] A network model acquisition unit, used to acquire a long short-term memory network model;

[0103] A model parameter determination unit, used to train the operation factor layer sample set respectively using the long short-term memory network model to determine the model weight and model bias;

[0104] The model iteration training unit is used to iteratively train the model weights and model biases through a back propagation algorithm until a preset model accuracy rate is reached to obtain a set of functional models of the equipment operation factors.

[0105] Furthermore, the system also includes:

[0106] A model data prediction unit, used for inputting the equipment periodic variation characteristics into the power equipment operation twin model for prediction, and outputting the power equipment prediction operation data;

[0107] A data loss analysis unit, configured to obtain equipment operation loss data by performing data loss analysis on the predicted operation data of the electric power equipment;

[0108] A loss training unit is used to train the equipment operation loss data based on the power equipment operation twin model to obtain the power equipment operation optimization twin model.

[0109] The foregoing Figure 1The various variations and specific examples of the method for managing a digital twin feature layer in Example 1 are also applicable to the management system of a digital twin feature layer in this embodiment. Through the above detailed description of the method for managing a digital twin feature layer, those skilled in the art can clearly know the implementation method of the management system of a digital twin feature layer in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0110] In addition, the present application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and run on the processor. The transceiver, the memory, and the processor are respectively connected via a bus. When the computer program is executed by the processor, each process of the above-mentioned method embodiment for controlling output data is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0111] Exemplary Electronic Devices

[0112] For details, see Figure 3 As shown, the present application also provides an electronic device, which includes a bus 1110 , a processor 1120 , a transceiver 1130 , a bus interface 1140 , a memory 1150 and a user interface 1160 .

[0113] In the present application, the electronic device further includes: a computer program stored in the memory 1150 and executable on the processor 1120, and when the computer program is executed by the processor 1120, each process of the above-mentioned method embodiment for controlling output data is implemented.

[0114] The transceiver 1130 is configured to receive and send data under the control of the processor 1120 .

[0115] In the present application, a bus architecture (represented by bus 1110 ) may include any number of interconnected buses and bridges, and bus 1110 connects various circuits including one or more processors represented by processor 1120 and a memory represented by memory 1150 .

[0116] Bus 1110 represents one or more of any of several types of bus structures, including a memory bus and memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. Such architectures include, by way of example and not limitation, an Industry Standard Architecture bus, a Micro Channel Architecture bus, an expansion bus, a Video Electronics Standards Association, a Peripheral Component Interconnect bus.

[0117] The processor 1120 may be an integrated circuit chip having signal processing capabilities. In the implementation process, each step of the above method embodiment may be completed by an integrated logic circuit of hardware in the processor or instructions in the form of software. The above processors include: a general-purpose processor, a central processing unit, a network processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array, a complex programmable logic device, a programmable logic array, a microcontroller unit or other programmable logic device, a discrete gate, a transistor logic device, and a discrete hardware component. The various methods, steps, and logic block diagrams disclosed in this application may be implemented or executed. For example, the processor may be a single-core processor or a multi-core processor, and the processor may be integrated into a single chip or located on multiple different chips.

[0118] Processor 1120 may be a microprocessor or any conventional processor. The method steps disclosed in the present application may be directly executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may be located in a readable storage medium known in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, a register, etc. The readable storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0119] The bus 1110 may also connect various other circuits such as peripheral devices, voltage regulators or power management circuits, and the bus interface 1140 provides an interface between the bus 1110 and the transceiver 1130, which are well known in the art. Therefore, this application will not further describe them.

[0120] The transceiver 1130 may be one element or multiple elements, such as multiple receivers and transmitters, and provides a unit for communicating with various other devices on a transmission medium. For example, the transceiver 1130 receives external data from other devices, and the transceiver 1130 is used to send data processed by the processor 1120 to other devices. Depending on the nature of the computer device, a user interface 1160 may also be provided, such as a touch screen, a physical keyboard, a display, a mouse, a speaker, a microphone, a trackball, a joystick, or a stylus.

[0121] It should be understood that in the present application, the memory 1150 may further include a memory remotely arranged relative to the processor 1120, and these remotely arranged memories may be connected to the server through a network. One or more parts of the above network may be a self-organizing network, an intranet, an extranet, a virtual private network, a local area network, a wireless local area network, a wide area network, a wireless wide area network, a metropolitan area network, the Internet, a public switched telephone network, a plain old telephone service network, a cellular telephone network, a wireless network, a wireless fidelity network, and a combination of two or more of the above networks. For example, the cellular telephone network and the wireless network may be a global mobile communication device, a code division multiple access device, a global microwave interconnection access device, a general packet radio service device, a wideband code division multiple access device, a long term evolution device, a LTE frequency division duplex device, a LTE time division duplex device, an advanced long term evolution device, a universal mobile communication device, an enhanced mobile broadband device, a massive machine type communication device, an ultra-reliable low latency communication device, and the like.

[0122] It should be understood that the memory 1150 in the present application may be a volatile memory or a non-volatile memory, or may include both a volatile memory and a non-volatile memory. Among them, the non-volatile memory includes: a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, or a flash memory.

[0123] Volatile memory includes random access memory, which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory, dynamic random access memory, synchronous dynamic random access memory, double data rate synchronous dynamic random access memory, enhanced synchronous dynamic random access memory, synchronously linked dynamic random access memory, and direct memory bus random access memory. The memory 1150 of the electronic device described in the present application includes, but is not limited to, the above and any other suitable types of memory.

[0124] In the present application, the memory 1150 stores the following elements of the operating system 1151 and the application program 1152: executable modules, data structures, or subsets thereof, or extended sets thereof.

[0125] Specifically, the operating system 1151 includes various device programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application 1152 includes various application programs, such as a media player and a browser, which are used to implement various application services. The program implementing the method of the present application may be included in the application 1152. The application 1152 includes applets, objects, components, logic, data structures, and other computer device executable instructions that perform specific tasks or implement specific abstract data types.

[0126] In addition, the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned method embodiment for controlling output data are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0127] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for managing a digital twin feature layer, characterized in that: The method comprises: Acquire the power equipment operation characteristic data stream through the sensor group, wherein the power equipment operation characteristic data stream includes the equipment operation status data stream and the power equipment attribute information; Constructing an equipment operation attribute classifier, searching and classifying the power equipment operation characteristic data stream according to the equipment operation attribute classifier, and obtaining equipment operation characteristic attribute information; Acquire a feature layer coding rule, encode the device operation feature attribute information based on the feature layer coding rule, and obtain the device operation attribute feature code information, wherein the feature layer reflects the manifestation of the physical object in the digital space, is the basis for realizing virtual-real mapping, real-time synchronization, symbiotic evolution and closed-loop optimization, and includes the appearance, performance, location, and abnormal information of the physical object; Integrate the power equipment operation characteristic data stream according to the equipment operation attribute characteristic code information to obtain an integrated equipment operation characteristic layer data stream. Specifically, integrate the data streams with the same equipment operation attribute characteristic code into one category to obtain the equipment operation characteristic layer data stream. Using digital twin technology to simulate and model the data flow of the equipment operation feature layer to generate a power equipment operation twin model; The power equipment operation twin model is updated and learned through the equipment periodic change characteristics to obtain the power equipment operation optimization twin model, and the power equipment operation is controlled based on the power equipment operation optimization twin model; The step of constructing a device operation attribute classifier includes: Determine a device operation characteristic attribute set and a device characteristic attribute set according to the device operation status data stream and the power device attribute information; Performing principal component analysis on the equipment operation feature attribute set and the equipment feature attribute set to obtain an equipment dimension reduction data feature set, wherein the equipment dimension reduction data feature set includes operation attribute features, operation space-time features, and equipment attribute features; Performing information theory coding operations on the operation attribute features, operation space-time features and equipment attribute features respectively to obtain classifier feature node information; Based on the classifier feature node information, construct the equipment operation attribute classifier; The step of generating a twin model of power equipment operation includes: Extracting entity elements from the device operation feature layer data stream to obtain the device operation entity layer data stream; Simulate the data flow of the equipment operation entity layer according to the preset modeling granularity level to generate a power equipment topology network source model; Acquire power equipment function factor information, classify the equipment operation feature layer data stream according to the power equipment function factor information, and acquire an operation factor layer sample set; The operation factor layer sample set is trained to obtain a set of equipment operation factor function models, and the power equipment topology network source model and the set of equipment operation factor function models are integrated using digital twin technology to generate the power equipment operation twin model.

2. The method according to claim 1, characterized in that The obtaining of the classifier feature node information includes: Extracting knowledge from the operation attribute features, operation spatiotemporal features, and equipment attribute features respectively to obtain an equipment operation attribute entity set; Filling each attribute entity in the device operation attribute entity set with content to obtain a device operation attribute entity content set; An information theory coding operation is performed based on the device operation attribute entity content set to obtain the classifier feature node information.

3. The method according to claim 2, characterized in that The step of obtaining the feature layer coding rule includes: Determine a layer coding content system based on the device dimension reduction data feature set, the device operation attribute entity set, and the device operation attribute entity content set; Dividing the coding level according to the layer coding content system to obtain feature layer coding level information; Based on the layer coding content system and the feature layer coding level information, setting a layer feature code identification criterion; The feature layer encoding rule is determined based on the feature layer encoding level information and the layer feature code identification criterion.

4. The method according to claim 1, characterized in that The obtaining of the power equipment operation optimization twin model comprises: Inputting the equipment periodic variation characteristics into the power equipment operation twin model for prediction, and outputting the power equipment prediction operation data; Obtaining equipment operation loss data by performing data loss analysis on the predicted operation data of the electric power equipment; The equipment operation loss data is trained based on the power equipment operation twin model to obtain the power equipment operation optimization twin model.

5. A management system for digital twin feature layers, characterized in that: A method for managing a digital twin feature layer according to any one of claims 1 to 4, the system comprising: An operation characteristic data stream acquisition module is used to acquire the operation characteristic data stream of the power equipment through the sensor group, wherein the operation characteristic data stream of the power equipment includes the equipment operation status data stream and the power equipment attribute information; A data stream retrieval and classification module is used to construct an equipment operation attribute classifier, retrieve and classify the power equipment operation characteristic data stream according to the equipment operation attribute classifier, and obtain equipment operation characteristic attribute information; A feature attribute information encoding module is used to obtain a feature layer encoding rule, encode the device operation feature attribute information based on the feature layer encoding rule, and obtain the device operation attribute feature code information, wherein the feature layer reflects the manifestation of the physical object in the digital space, is the basis for realizing virtual-real mapping, real-time synchronization, symbiotic evolution and closed-loop optimization, and contains the appearance, performance, location, and abnormal information of the physical object; A data stream integration module, used to integrate the power equipment operation characteristic data stream according to the equipment operation attribute characteristic code information, and obtain the integrated equipment operation characteristic layer data stream, specifically, integrating the data streams with the same equipment operation attribute characteristic code into one category, and obtaining the equipment operation characteristic layer data stream; A simulation modeling module, used to use digital twin technology to simulate and model the data flow of the equipment operation feature layer to generate a power equipment operation twin model; The power equipment operation control module is used to update and learn the power equipment operation twin model through the equipment periodic change characteristics, obtain the power equipment operation optimization twin model, and perform power equipment operation control based on the power equipment operation optimization twin model.

6. An electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, wherein: When the computer program is executed by the processor, the steps in the method for managing a digital twin feature layer as described in any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in a method for managing a digital twin feature layer as described in any one of claims 1 to 4 are implemented.

Images