A digital twin-based electrical equipment twin hierarchical management method and system

Abstract

The present application provides a method and system for hierarchical management of electrical equipment twins based on digital twins, which collects the operating status data set of the target electrical equipment; determines the information load of each operating status data, determines the twin generation data according to all the information load, and generates the data twin of the target electrical equipment through the twin generation data and the twin database; predicts the state of the target electrical equipment according to the data twin, obtains the state prediction label set, and then determines the electrical equipment state index according to the state prediction label set and the historical operating data of the target electrical equipment, and converts the electrical equipment state index into the electrical equipment fault prediction amount using the fault data of the target electrical equipment; hierarchical monitoring of the data twin of the target electrical equipment is performed according to the electrical equipment fault prediction amount. The above scheme can improve the classification accuracy of the data twin of the electrical equipment while ensuring the robustness and prediction accuracy of the data twin.

Description

Technical Field

[0001] The present application relates to the field of digital twin technology, and more specifically, to a method and system for hierarchical management of electrical equipment twins based on digital twins. Background Art

[0002] Digital Twin is a technical concept that refers to the creation of a digital replica of a physical object or system in a virtual space through digital technology. This digital replica can reflect the status, performance and behavior of its physical counterpart in real time.

[0003] Hierarchical management of electrical equipment twins based on digital twins is an advanced equipment management method. By mapping the various parameters and operating status of physical electrical equipment into digital models in real time, it can realize real-time monitoring, predictive maintenance and optimization management of equipment. Hierarchical management divides twins into multiple monitoring levels. Different monitoring levels correspond to different monitoring and processing strategies. Each monitoring level requires different technology and resource investment to gradually improve the intelligence and refinement level of electrical equipment management to ensure timely detection of electrical equipment failures. In the prior art, electrical equipment generates a large amount of real-time data during operation. Faced with a huge amount of data, the system cannot efficiently store and manage this data to ensure the accuracy of data twin training and prediction. In addition, abnormal fault conditions at all stages of electrical equipment will affect the hierarchical monitoring of electrical equipment, and the system cannot accurately determine the monitoring level of electrical equipment twins. Therefore, how to improve the classification accuracy of data twins of electrical equipment under the premise of ensuring the robustness and prediction accuracy of data twins has become a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides a method and system for hierarchical management of electrical equipment twins based on digital twins, which can improve the classification accuracy of data twins of electrical equipment while ensuring the robustness and prediction accuracy of data twins.

[0005] In a first aspect, the present application provides a method for hierarchical management of electrical equipment twins based on digital twins, comprising the following steps:

[0006] Collecting the operating data of the target electrical equipment in a working state to obtain an operating state data set of the target electrical equipment;

[0007] Determine the information load of each operating status data in the operating status data set, determine the twin generation data of the target electrical equipment according to all the information loads, and generate the data twin of the target electrical equipment through the twin generation data and the twin database of the target electrical equipment;

[0008] Performing state prediction on the target electrical equipment according to the data twin to obtain a state prediction label set of the target electrical equipment, and then determining the electrical equipment state index according to the state prediction label set and the historical operation data of the target electrical equipment, and converting the electrical equipment state index into an electrical equipment fault prediction amount using the fault data of the target electrical equipment;

[0009] The data twin of the target electrical equipment is monitored in a hierarchical manner according to the electrical equipment fault prediction quantity.

[0010] In some embodiments, determining the information load of each running status data in the running status data set specifically includes:

[0011] For each running status data in the running status data set, selecting one running status data as selected data;

[0012] determining a data correlation between the selected data and other operating status data in the operating status data set;

[0013] The information carrying capacity of the selected data is determined by all data correlations, and other running status data in the running status data set are continuously selected as selected data, thereby obtaining the information carrying capacity of each running status data in the running status data set.

[0014] In some embodiments, operating data of the target electrical equipment in a working state is collected by monitoring sensors.

[0015] In some embodiments, determining the twin generation data of the target electrical equipment according to all information loads specifically includes:

[0016] Sorting each operating status data in the operating status data set in descending order according to the corresponding information load, to obtain an operating data sequence of the target electrical equipment in a working state;

[0017] The operation data sequence is intercepted by a set information co-loading threshold to obtain the twin generation data of the target electrical equipment.

[0018] In some embodiments, generating a data twin of the target electrical equipment through the twin generation data and a twin database of the target electrical equipment specifically includes:

[0019] Obtain a digital twin model based on deep learning;

[0020] The deep learning-based digital twin model is trained according to the twin database of the target electrical equipment to obtain the trained digital twin model;

[0021] The twin generation data is input into the trained digital twin model to generate a data twin of the target electrical equipment.

[0022] In some embodiments, performing state prediction on the target electrical equipment based on the data twin is to input a standardized operating state data set into the data twin for state prediction.

[0023] In some embodiments, performing hierarchical monitoring on the data twin of the target electrical equipment according to the electrical equipment fault prediction quantity specifically includes:

[0024] Get a given fault level monitoring table;

[0025] Determining the fault monitoring level of the target electrical equipment by using the electrical equipment fault prediction quantity and the fault level monitoring table;

[0026] The digital twin of the target electrical equipment is monitored based on the fault monitoring level.

[0027] In a second aspect, the present application provides a digital twin-based electrical equipment twin hierarchical management system, including a hierarchical monitoring unit, wherein the hierarchical monitoring unit includes:

[0028] The acquisition module is used to acquire the operation data of the target electrical equipment in the working state, and obtain the operation state data set of the target electrical equipment;

[0029] a processing module, configured to determine the information load of each operating status data in the operating status data set, determine the twin generation data of the target electrical equipment according to all the information loads, and generate the data twin of the target electrical equipment through the twin generation data and the twin database of the target electrical equipment;

[0030] The processing module is further used to perform state prediction on the target electrical equipment according to the data twin to obtain a state prediction label set of the target electrical equipment, and then determine the electrical equipment state index according to the state prediction label set and the historical operation data of the target electrical equipment, and convert the electrical equipment state index into an electrical equipment fault prediction amount using the fault data of the target electrical equipment;

[0031] An execution module is used to perform hierarchical monitoring on the data twin of the target electrical equipment according to the electrical equipment fault prediction quantity.

[0032] In a third aspect, the present application provides a computer device, comprising a memory and a processor, the memory being used to store a computer program, the processor being used to call and run the computer program from the memory, so that the computer device executes the above-mentioned digital twin-based electrical equipment twin hierarchical management method.

[0033] In a fourth aspect, the present application provides a computer-readable storage medium, which stores instructions or codes. When the instructions or codes are run on a computer, the computer implements the above-mentioned digital twin-based electrical equipment twin hierarchical management method when executed.

[0034] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0035] The present application provides a digital twin-based electrical equipment twin hierarchical management method and system, which collects operating data of the target electrical equipment in a working state to obtain an operating status data set of the target electrical equipment; determines the information load capacity of each operating status data in the operating status data set, determines the twin generation data of the target electrical equipment based on all the information load capacities, and generates a data twin of the target electrical equipment through the twin generation data and the twin database of the target electrical equipment; predicts the state of the target electrical equipment based on the data twin to obtain a state prediction label set of the target electrical equipment, and then determines the electrical equipment state index based on the state prediction label set and the historical operating data of the target electrical equipment, and uses the fault data of the target electrical equipment to convert the electrical equipment state index into an electrical equipment fault prediction quantity; and performs hierarchical monitoring on the data twin of the target electrical equipment based on the electrical equipment fault prediction quantity.

[0036] It can be seen that in this application, the classification accuracy of the data twin of electrical equipment can be improved while ensuring the robustness and prediction accuracy of the data twin; wherein, the operating status data with high information load usually contains more repeated and useless status information, resulting in a waste of system computing resources, while the data points with low information load may contain more valuable information. By giving priority to the use of operating status data with low information load, the digital twin model can improve its ability to capture and predict the state of electrical equipment, which helps to reduce the classification error rate and improve the reliability of the data twin; then, based on the prediction and analysis of the data twin, the decision-making process is made more scientific and data-driven, reducing the errors and uncertainties caused by human factors. Through accurate state prediction and electrical equipment fault prediction, potential fault problems can be identified in advance. A large amount of historical operating data and fault data are used for data twin training and calibration to ensure that the data twin has strong robustness to different operating states and fault modes, thereby improving the accuracy and reliability of the prediction; finally, the data twin of the target electrical equipment is graded and monitored through accurate electrical equipment fault prediction, improving the classification accuracy of the data twin of the electrical equipment and ensuring the safety and reliability of the electrical equipment. To sum up, the technical solution adopted in this application can improve the classification accuracy of data twins of electrical equipment while ensuring the robustness and prediction accuracy of data twins. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0038] Figure 1 is an exemplary flow chart of a method for hierarchical management of electrical equipment twins based on digital twins according to some embodiments of the present application;

[0039] Figure 2 is an exemplary flow chart for determining information load according to some embodiments of the present application;

[0040] Figure 3 is an exemplary flow chart for determining a predicted amount of electrical equipment failure according to some embodiments of the present application;

[0041] Figure 4 is a schematic diagram of exemplary hardware and / or software of a hierarchical monitoring unit according to some embodiments of the present application;

[0042] Figure 5 It is a structural schematic diagram of a computer device for implementing a hierarchical management method of electrical equipment twins based on digital twins as shown in some embodiments of the present application. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0044] The embodiment of the present application provides a method and system for hierarchical management of electrical equipment twins based on digital twins, the core of which is to collect the operating data of the target electrical equipment in the working state to obtain the operating state data set of the target electrical equipment; determine the information load of each operating state data in the operating state data set, determine the twin generation data of the target electrical equipment according to all the information loads, and generate the data twin of the target electrical equipment through the twin generation data and the twin database of the target electrical equipment; predict the state of the target electrical equipment according to the data twin to obtain the state prediction label set of the target electrical equipment, and then determine the electrical equipment state index according to the state prediction label set and the historical operating data of the target electrical equipment, and use the fault data of the target electrical equipment to convert the electrical equipment state index into the electrical equipment fault prediction amount; and perform hierarchical monitoring on the data twin of the target electrical equipment according to the electrical equipment fault prediction amount. The above scheme can improve the classification accuracy of the data twin of the electrical equipment while ensuring the robustness and prediction accuracy of the data twin.

[0045] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 , which is an exemplary flow chart of a method for hierarchical management of electrical equipment twins based on digital twins according to some embodiments of the present application. The method 100 for hierarchical management of electrical equipment twins based on digital twins mainly includes the following steps:

[0046] In step 101, operation data of a target electrical equipment in a working state is collected to obtain an operation state data set of the target electrical equipment.

[0047] In the specific implementation, the operating data of the target electrical equipment in the working state is collected through monitoring sensors; first, the appropriate installation location of the monitoring sensor is selected according to the structure of the target electrical equipment and the key monitoring points, and it is ensured that the monitoring sensor is installed firmly to avoid affecting the measurement accuracy; then, the data collection frequency is set according to the monitoring requirements to ensure real-time and data integrity, so as to collect the operating data of the target electrical equipment in the working state, and then the collection of all the operating data is used as the operating status data set of the target electrical equipment.

[0048] In step 102, the information load capacity of each operating status data in the operating status data set is determined, the twin generation data of the target electrical equipment is determined according to all the information load capacities, and the data twin of the target electrical equipment is generated through the twin generation data and the twin database of the target electrical equipment.

[0049] Preferably, in some embodiments, reference Figure 2As shown, this figure is an exemplary flow chart for determining the information load capacity in some embodiments of the present application. In this embodiment, determining the information load capacity of each running status data in the running status data set can be implemented by the following steps:

[0050] In step 1021, for each running status data in the running status data set, one running status data is selected as selected data;

[0051] In step 1022, determining the data correlation between the selected data and other operating status data in the operating status data set;

[0052] In step 1023, the information carrying capacity of the selected data is determined through all data correlations, and other operating status data in the operating status data set are continuously selected as selected data, thereby obtaining the information carrying capacity of each operating status data in the operating status data set.

[0053] It should be noted that, in the present application, information co-carrying capacity indicates the degree of information overlap between the operating status data and the operating status data set as a whole; data correlation indicates the degree of data correlation between the operating status data; in specific implementation, first, for each operating status data in the operating status data set, one operating status data can be selected as the selected data; then, the cosine similarity between the selected data and other operating status data in the operating status data set can be calculated, so that the cosine similarity can be used as the data correlation between the selected data and other operating status data in the operating status data set; finally, the standard deviation of all data correlations can be used as the information co-carrying capacity of the selected data, so as to continue to select other operating status data in the operating status data set as the selected data, and the information co-carrying capacity of each operating status data in the operating status data set can be obtained in the above manner.

[0054] Optionally, in some embodiments, the following method can be used to determine the twin generation data of the target electrical equipment according to all information loads, namely:

[0055] Sorting each operating status data in the operating status data set in descending order according to the corresponding information load, to obtain an operating data sequence of the target electrical equipment in a working state;

[0056] The operation data sequence is intercepted by a set information co-loading threshold to obtain the twin generation data of the target electrical equipment.

[0057] In the specific implementation, first, each operating status data in the operating status data set is sorted in descending order according to the corresponding information co-load, so as to obtain a data sequence, which can be used as the operating data sequence of the target electrical equipment in the working state; then, an information co-load threshold can be set through historical experience and data analysis to intercept the operating data sequence, so that the operating data sequence is intercepted by the set information co-load threshold, that is, if the information co-load threshold is k, the last k operating status data in the operating data sequence are intercepted, and the degree of correlation between the intercepted operating status data is low, indicating that the degree of information overlap between the intercepted operating status data is low, that is, most of the operating status information of the target electrical equipment is covered by the intercepted operating status data, and the set of all intercepted operating status data is used as the twin generation data of the target electrical equipment, that is, the twin generation data is used to generate the operating status data of the twin of the target electrical equipment.

[0058] Optionally, in some embodiments, the data twin of the target electrical equipment is generated by using the twin generation data and the twin database of the target electrical equipment in the following manner, namely:

[0059] Obtain a digital twin model based on deep learning;

[0060] The deep learning-based digital twin model is trained according to the twin database of the target electrical equipment to obtain the trained digital twin model;

[0061] The twin generation data is input into the trained digital twin model to generate a data twin of the target electrical equipment.

[0062] In the specific implementation, first, a deep learning-based digital twin model suitable for electrical equipment state prediction and simulation can be selected, such as long short-term memory network, convolutional neural network, variational autoencoder, etc., so as to design the digital twin model architecture according to actual needs and determine the structure of the input layer, hidden layer and output layer; then, the twin database of the target electrical equipment can be obtained, which contains the historical operation data of the target electrical equipment, including various sensor data, such as current, voltage, temperature, vibration, etc., and the historical data is extracted from the twin database and divided into a training set and a validation set, so as to train the digital twin model using the training data set, optimize the digital twin model parameters through back propagation and gradient descent algorithms, evaluate the performance of the digital twin model using the validation data set, adjust the digital twin model structure and hyperparameters to improve the prediction accuracy and robustness, and obtain the trained digital twin model in the above manner; finally, the twin generation data collected in real time is input into the trained digital twin model, and the trained digital twin model is used to infer the input data to generate the data twin of the target electrical equipment, including the real-time state, predicted state and health index, etc.

[0063] It should be noted that operating status data with high information load usually contains more repeated and useless status information, resulting in a waste of system computing resources, while data points with low information load may contain more valuable information. By giving priority to the use of operating status data with low information load, the digital twin model's ability to capture and predict the status of electrical equipment can be improved, which helps reduce the classification error rate and improves the reliability of the data twin.

[0064] In step 103, the state of the target electrical equipment is predicted based on the data twin to obtain a state prediction label set of the target electrical equipment, and then the electrical equipment state index is determined by the state prediction label set and the historical operation data of the target electrical equipment, and the fault data of the target electrical equipment is used to convert the electrical equipment state index into an electrical equipment fault prediction value.

[0065] Optionally, in some embodiments, state prediction of the target electrical equipment based on the data twin is to input a standardized operating status data set into the data twin for state prediction, and obtain a state prediction label set of the target electrical equipment; in specific implementation, first, the operating status data set can be normalized, that is, the operating status data set can be standardized; then, the standardized operating status data set can be input into the data twin for state prediction, that is, the data twin infers the input standardized data and outputs a state prediction result; finally; a state prediction label set is generated according to the state prediction result output by the data twin, and the state prediction label set includes different states of the electrical equipment such as normal, warning, fault, etc.

[0066] Optionally, in some embodiments, the electrical equipment state index may be determined by the state prediction tag set and the historical operation data of the target electrical equipment in the following manner, namely:

[0067] Determining an estimated state index of the target electrical equipment by using historical operation data of the target electrical equipment and the state prediction label set;

[0068] The estimated status index of the target electrical equipment is converted into an electrical equipment status index.

[0069] It should be noted that, in the present application, the electrical equipment status index represents the health of the target electrical equipment status; in specific implementation, first, the historical operation data of the target electrical equipment can be obtained in the system database, and the historical operation data contains multiple historical operation data points, and the number is the same as that of the state prediction labels in the state prediction label set; then, each state prediction label in the state prediction label set can be multiplied by the historical operation data point in the order of the data set, for example, the first state prediction label in the state prediction label set is multiplied by the first historical operation data point in the historical operation data, and all the results are used as the estimated state index of the target electrical equipment, and the estimated state index represents the estimated health of the target electrical equipment; finally, the operating years of the target electrical equipment are extracted from the historical operating data of the target electrical equipment, so that the ratio of the estimated state index to the operating years can be used as the electrical equipment state index.

[0070] Preferably, in some embodiments, reference Figure 3 As shown in FIG. 1 , this figure is an exemplary flow chart for determining the electrical equipment fault prediction amount in some embodiments of the present application. In this embodiment, the electrical equipment state index is converted into the electrical equipment fault prediction amount using the fault data of the target electrical equipment, which can be implemented by the following steps:

[0071] In step 1031, a probability density function of target electrical equipment failure is established according to the failure data of the target electrical equipment;

[0072] In step 1032, a fault prediction weight is determined by using the probability density function;

[0073] In step 1033, the electrical equipment status index is converted into an electrical equipment fault prediction value according to the fault prediction weight.

[0074] It should be noted that, in the present application, the electrical equipment fault prediction amount represents the predicted degree of fault loss of the target electrical equipment; in specific implementation, first, the fault data of the target electrical equipment can be obtained, and then the fault data can be used to establish a probability density function of the target electrical equipment failure, and the probability density function is used to describe the probability distribution of a certain variable (such as the time of fault occurrence) at each value point; then, by analyzing the established probability density function, the fault occurrence probability corresponding to different state indexes is determined, that is, according to the probability of fault occurrence, the fault prediction weight is determined, and the fault prediction weight reflects the degree of correlation between the electrical equipment state index and the fault occurrence; finally, based on the determined fault prediction weight, the electrical equipment state index is converted into the electrical equipment fault prediction amount, specifically, the product of the electrical equipment state index and the fault prediction weight can be used as the electrical equipment fault prediction amount.

[0075] It should be noted that the prediction and analysis based on data twins make the decision-making process more scientific and data-driven, reducing errors and uncertainties caused by human factors. Through accurate status prediction and electrical equipment fault prediction, potential fault problems can be identified in advance, and preventive maintenance measures can be taken in time to avoid sudden equipment failure and shutdown, thereby reducing maintenance costs and downtime. A large amount of historical operating data and fault data is used for data twin training and calibration to ensure that the data twin is highly robust to different operating states and failure modes, thereby improving the accuracy and reliability of the prediction.

[0076] In step 104, the data twin of the target electrical equipment is hierarchically monitored according to the electrical equipment fault prediction quantity.

[0077] Preferably, in some embodiments, hierarchical monitoring of the data twin of the target electrical equipment according to the electrical equipment fault prediction quantity may be performed in the following manner, namely:

[0078] Get a given fault level monitoring table;

[0079] Determining the fault monitoring level of the target electrical equipment by using the electrical equipment fault prediction quantity and the fault level monitoring table;

[0080] The digital twin of the target electrical equipment is monitored based on the fault monitoring level.

[0081] In the specific implementation, first, a predefined fault level monitoring table is obtained, which lists the monitoring levels corresponding to different fault prediction quantities, such as low risk, medium risk, high risk, etc.; then, the fault prediction quantity of the electrical equipment is compared with the fault level monitoring table to determine the fault monitoring level of the target electrical equipment. For example, if the fault prediction quantity is between 0 and 0.3, it belongs to the low risk level; if the fault prediction quantity is between 0.3 and 0.7, it belongs to the medium risk level; if the fault prediction quantity is above 0.7, it belongs to the high risk level; finally, according to the determined fault monitoring level, corresponding monitoring strategies and measures are taken, as follows:

[0082] Low risk level: Regularly monitor the digital twin of the target electrical equipment and maintain regular inspection frequency. No additional preventive measures are required.

[0083] Medium risk level: Increase the monitoring frequency of the digital twin of the target electrical equipment. Additional inspections or maintenance of the target electrical equipment may be required to ensure that problems are addressed in the early stages.

[0084] High risk level: Emergency monitoring of the digital twin of the target electrical equipment may require immediate shutdown of the target electrical equipment for inspection, comprehensive diagnosis and repair.

[0085] It can be seen that in this application, the classification accuracy of the data twin of electrical equipment can be improved while ensuring the robustness and prediction accuracy of the data twin; wherein, the operating status data with high information load usually contains more repeated and useless status information, resulting in a waste of system computing resources, while the data points with low information load may contain more valuable information. By giving priority to the use of operating status data with low information load, the digital twin model can improve its ability to capture and predict the state of electrical equipment, which helps to reduce the classification error rate and improve the reliability of the data twin; then, based on the prediction and analysis of the data twin, the decision-making process is made more scientific and data-driven, reducing the errors and uncertainties caused by human factors. Through accurate state prediction and electrical equipment fault prediction, potential fault problems can be identified in advance. A large amount of historical operating data and fault data are used for data twin training and calibration to ensure that the data twin has strong robustness to different operating states and fault modes, thereby improving the accuracy and reliability of the prediction; finally, the data twin of the target electrical equipment is graded and monitored through accurate electrical equipment fault prediction, improving the classification accuracy of the data twin of the electrical equipment and ensuring the safety and reliability of the electrical equipment. To sum up, the technical solution adopted in this application can improve the classification accuracy of data twins of electrical equipment while ensuring the robustness and prediction accuracy of data twins.

[0086] In addition, in another aspect of the present application, in some embodiments, the present application provides a digital twin-based electrical equipment twin hierarchical management system, the digital twin-based electrical equipment twin hierarchical management system includes a hierarchical monitoring unit, reference Figure 4 , which is a schematic diagram of exemplary hardware and / or software of a hierarchical monitoring unit according to some embodiments of the present application, the hierarchical monitoring unit 400 includes: a collection module 401, a processing module 402 and an execution module 403, which are described as follows:

[0087] The acquisition module 401 in this application is mainly used to collect the operating data of the target electrical equipment in the working state, and obtain the operating state data set of the target electrical equipment;

[0088] The processing module 402 in the present application is used to determine the information load of each operating status data in the operating status data set, determine the twin generation data of the target electrical equipment according to all the information loads, and generate the data twin of the target electrical equipment through the twin generation data and the twin database of the target electrical equipment;

[0089] It should be noted that the processing module 402 in the present application is also used to perform state prediction on the target electrical equipment based on the data twin, obtain a state prediction label set of the target electrical equipment, and then determine the electrical equipment state index based on the state prediction label set and the historical operation data of the target electrical equipment, and use the fault data of the target electrical equipment to convert the electrical equipment state index into an electrical equipment fault prediction amount;

[0090] Execution module 403, in the present application, the execution module 403 is mainly used to perform hierarchical monitoring on the data twin of the target electrical equipment according to the electrical equipment fault prediction quantity.

[0091] The above describes in detail the examples of the method and system for hierarchical management of electrical equipment twins based on digital twins provided in the embodiments of the present application. It can be understood that in order to realize the above functions, the corresponding device includes hardware structures and / or software modules corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0092] In some embodiments, the present application also provides a computer device, comprising a memory and a processor, the memory being used to store a computer program, and the processor being used to call and run the computer program from the memory, so that the computer device executes the above-mentioned digital twin-based electrical equipment twin hierarchical management method.

[0093] In some embodiments, reference Figure 5 , the dotted line in the figure indicates that the unit or module is optional. The figure is a structural diagram of a computer device according to a digital twin-based electrical equipment twin hierarchical management method provided in an embodiment of the present application. The digital twin-based electrical equipment twin hierarchical management method described in the above embodiment can be Figure 5 The computer device 500 shown in the figure is implemented, and the computer device 500 includes at least one processor 501, a memory 502 and at least one communication unit 505. The computer device 500 can be a terminal device, a server or a chip.

[0094] The processor 501 may be a general-purpose processor or a special-purpose processor. For example, the processor 501 may be a central processing unit (CPU), which may be used to control the computer device 500, execute software programs, and process data of the software programs. The computer device 500 may also include a communication unit 505 to implement signal input (reception) and output (transmission).

[0095] For example, the computer device 500 may be a chip, the communication unit 505 may be an input and / or output circuit of the chip, or the communication unit 505 may be a communication interface of the chip, and the chip may be a component of a terminal device, a network device, or other devices.

[0096] For another example, the computer device 500 may be a terminal device or a server, and the communication unit 505 may be a transceiver of the terminal device or the server, or the communication unit 505 may be a transceiver circuit of the terminal device or the server.

[0097] The computer device 500 may include one or more memories 502, on which a program 504 is stored. The program 504 can be executed by the processor 501 to generate instructions 503, so that the processor 501 performs the method described in the above method embodiment according to the instructions 503. Optionally, data (such as a target audit model) can also be stored in the memory 502. Optionally, the processor 501 can also read the data stored in the memory 502, and the data can be stored at the same storage address as the program 504, or the data can be stored at a different storage address from the program 504.

[0098] The processor 501 and the memory 502 may be provided separately or integrated together, for example, integrated on a system on chip (SOC) of the terminal device.

[0099] It should be understood that each step of the above method embodiment can be completed by a hardware-based logic circuit or software-based instructions in the processor 501. The processor 501 can be a central processing unit, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, such as discrete gates, transistor logic devices or discrete hardware components.

[0100] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0101] For example, in some embodiments, the present application also provides a computer-readable storage medium, which stores instructions or codes. When the instructions or codes are run on a computer, the computer implements the above-mentioned digital twin-based electrical equipment twin hierarchical management method when executing.

[0102] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0103] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for hierarchical management of electrical equipment twins based on digital twins, characterized in that: The steps include: Collecting the operating data of the target electrical equipment in a working state to obtain an operating state data set of the target electrical equipment; Determine the information load of each operating status data in the operating status data set, determine the twin generation data of the target electrical equipment according to all the information loads, and generate the data twin of the target electrical equipment through the twin generation data and the twin database of the target electrical equipment; Performing state prediction on the target electrical equipment according to the data twin to obtain a state prediction label set of the target electrical equipment, and then determining the electrical equipment state index according to the state prediction label set and the historical operation data of the target electrical equipment, and converting the electrical equipment state index into an electrical equipment fault prediction amount using the fault data of the target electrical equipment; Performing hierarchical monitoring on the data twin of the target electrical equipment according to the electrical equipment fault prediction quantity; Wherein, determining the information load of each running status data in the running status data set specifically includes: For each running status data in the running status data set, selecting one running status data as selected data; determining a data correlation between the selected data and other operating status data in the operating status data set; Determine the information carrying capacity of the selected data through all data correlations, continue to select other running status data in the running status data set as selected data, and then obtain the information carrying capacity of each running status data in the running status data set; Among them, the twin generation data of the target electrical equipment is determined based on all the information and load, including: Sorting each operating status data in the operating status data set in descending order according to the corresponding information load, to obtain an operating data sequence of the target electrical equipment in a working state; The operation data sequence is intercepted by a set information co-loading threshold to obtain the twin generation data of the target electrical equipment.

2. The method according to claim 1, characterized in that The operating data of the target electrical equipment in working condition is collected through monitoring sensors.

3. The method according to claim 1, characterized in that Generating the data twin of the target electrical equipment through the twin generation data and the twin database of the target electrical equipment specifically includes: Obtain a digital twin model based on deep learning; The deep learning-based digital twin model is trained according to the twin database of the target electrical equipment to obtain the trained digital twin model; The twin generation data is input into the trained digital twin model to generate a data twin of the target electrical equipment.

4. The method according to claim 1, characterized in that Performing state prediction on the target electrical equipment based on the data twin is to input the standardized operating state data set into the data twin for state prediction.

5. The method according to claim 1, characterized in that The hierarchical monitoring of the data twin of the target electrical equipment according to the electrical equipment fault prediction quantity specifically includes: Get a given fault level monitoring table; Determining the fault monitoring level of the target electrical equipment by using the electrical equipment fault prediction quantity and the fault level monitoring table; The digital twin of the target electrical equipment is monitored based on the fault monitoring level.

6. A digital twin-based electrical equipment twin hierarchical management system, which is managed by the method described in any one of claims 1 to 5. The digital twin-based electrical equipment twin hierarchical management system includes a hierarchical monitoring unit, characterized in that: The hierarchical monitoring unit comprises: The acquisition module is used to acquire the operation data of the target electrical equipment in the working state, and obtain the operation state data set of the target electrical equipment; a processing module, configured to determine the information load of each operating status data in the operating status data set, determine the twin generation data of the target electrical equipment according to all the information loads, and generate the data twin of the target electrical equipment through the twin generation data and the twin database of the target electrical equipment; The processing module is further used to perform state prediction on the target electrical equipment according to the data twin to obtain a state prediction label set of the target electrical equipment, and then determine the electrical equipment state index according to the state prediction label set and the historical operation data of the target electrical equipment, and convert the electrical equipment state index into an electrical equipment fault prediction amount using the fault data of the target electrical equipment; An execution module is used to perform hierarchical monitoring on the data twin of the target electrical equipment according to the electrical equipment fault prediction quantity.

7. A computer device, characterized in that: The computer device includes a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the digital twin-based electrical equipment twin hierarchical management method described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions or codes, which, when executed on a computer, enable the computer to implement the digital twin-based hierarchical management method for electrical equipment twins as described in any one of claims 1 to 5.

Images