A monitoring method, device and medium for substation

Abstract

The present application discloses a monitoring method, device and medium for a substation; it relates to the field of substations and solves the problem of realizing global status perception of substations through digital twin technology. By establishing a three-dimensional static model based on the characteristics of the equipment itself, the structure and appearance of the equipment can be more intuitively understood. By establishing an average association relationship model, the operating status and performance of the equipment can be predicted and evaluated, and the topology model can describe the connection and interaction relationship between the equipment. Through twin modeling, the operating status of the equipment can be monitored in real time, future performance changes can be predicted, and system optimization and troubleshooting can be performed. It provides more comprehensive, accurate and real-time monitoring and management capabilities for substation automation systems. This helps to improve the efficiency and reliability of the system, reduce failures and maintenance costs, and enhance the stability and reliability of power supply.

Description

Technical Field

[0001] The present application relates to the field of substations, and in particular to a monitoring method, device and medium for substations. Background Art

[0002] In recent years, my country's energy internet construction has been accelerating, and at the same time, the types and scale of power equipment have also increased significantly, which has put forward higher requirements for the safe and stable operation of the power grid system. Due to the large number and wide distribution of power automation equipment, the monitoring and management of equipment has become very difficult. These devices may be distributed in different geographical locations, and the number is large, making it difficult for traditional monitoring methods to achieve comprehensive coverage.

[0003] Digital twin is a technology that realizes real-time monitoring, prediction and maintenance of equipment by establishing an accurate mapping relationship between physical equipment and digital models. However, it has not been fully applied in the commissioning and operation and maintenance of automation equipment. Digital twin technology can establish a virtual model that accurately matches the physical entity. However, digital twin technology has not yet been applied to the commissioning and operation and maintenance of automation equipment, which makes it difficult to achieve accurate matching between the digital twin of the automation equipment system and the physical entity in actual operation.

[0004] It can be seen that how to achieve global status perception of substations through digital twin technology is a technical problem that needs to be solved urgently by people in this field. Summary of the invention

[0005] The purpose of this application is to provide a substation monitoring method, device and medium to solve the problem of achieving global status perception of the substation through digital twin technology.

[0006] In order to solve the above technical problems, the present application provides a monitoring method for a substation, comprising:

[0007] Obtain a three-dimensional static model based on the ontological feature information of the substation automation equipment;

[0008] Establishing an average association relationship model according to the resource information of the substation automation equipment;

[0009] Establishing a topology model according to the three-dimensional static model and resource information of the substation automation equipment;

[0010] Integrating the average association relationship model and the topology model to obtain a twin model of a substation automation system;

[0011] Perform global status perception on the twin model of the substation automation system to obtain the real-time operating status and parameters of the substation automation equipment.

[0012] As an optional solution, in the above-mentioned substation monitoring method based on digital twin technology, the average association relationship model is established according to the resource information of the substation automation equipment, including:

[0013] Obtaining a multidimensional data set according to the resource information of the substation automation equipment;

[0014] Resampling the multidimensional data set multiple times to obtain corresponding resampled data sets;

[0015] Establishing an initial association relationship model corresponding to the resource information and the equipment factor according to each of the resampled data sets, wherein the equipment factor is a preset condition affecting the operation of the automation equipment;

[0016] After averaging the initial association relationship models, an average initial association relationship model between the resource information of the current substation automation equipment and the equipment factors is obtained;

[0017] According to the substation automation equipment probability value in the average initial association relationship model, each of the resampled data sets is divided to obtain a divided data set;

[0018] Establishing a partition association relationship model corresponding to the resource information and the device factors according to each of the partition data sets;

[0019] After averaging the plurality of partition association relationship models, the average association relationship model corresponding to the resource information of the current substation automation equipment and the equipment factors is obtained.

[0020] As an optional solution, in the above-mentioned substation monitoring method based on digital twin technology, after averaging the multiple partition association relationship models, the average association relationship model corresponding to the resource information of the current substation automation equipment and the equipment factor is obtained, and then it also includes:

[0021] Determining whether the average association relationship model is accurate according to a preset accuracy assessment;

[0022] If it is accurate, then the current average correlation model is output;

[0023] If it is inaccurate, the current average association relationship model is updated to the average initial association relationship model, and the step of returning to the step of dividing each of the resampled data sets according to the probability value of the substation automation equipment in the average initial association relationship model to obtain the divided data set is performed until the average association relationship model is judged to be accurate according to the preset accuracy evaluation.

[0024] As an optional solution, in the above-mentioned substation monitoring method based on digital twin technology, judging whether the average correlation model is accurate according to a preset accuracy evaluation includes:

[0025] Determine whether the first formula is valid;

[0026] The first formula is: (FC-CS) / 2 k ≤threshold;

[0027] Wherein, FC represents the data set of the average association relationship model; CS represents the data set of the average initial association relationship model; threshold represents the set threshold; k represents the number of states of the device factor of the automation device; 2 k Indicates the number of combinations of the resource information and the device factors;

[0028] If the first formula is established, it is determined that the average correlation relationship model is accurate;

[0029] If the first formula is not valid, it is determined that the average association relationship model is inaccurate.

[0030] As an optional solution, in the above-mentioned monitoring method for substation based on digital twin technology, the initial association relationship model corresponding to the resource information and the equipment factors is established according to each of the resampled data sets, including:

[0031] Inputting the resource information in the resampled data set and the combination of the preset device factors into a neural network as test data for training to obtain a corresponding model output result;

[0032] The model output result is used as the initial association relationship model.

[0033] As an optional solution, in the above-mentioned monitoring method for a substation based on digital twin technology, the establishment of a partition association relationship model corresponding to the resource information and the equipment factors according to each of the partition data sets includes:

[0034] Inputting the resource information in the divided data set and the combination of the preset device factors into a neural network as test data for training to obtain a corresponding model output result;

[0035] The model training result is used as the partition association relationship model.

[0036] As an optional solution, in the above-mentioned substation monitoring method based on digital twin technology, the global state perception of the substation automation system twin model is performed to obtain the real-time operating status and parameters of the substation automation equipment, and then it also includes:

[0037] The real-time operating status and parameters are displayed on a human-computer interaction interface.

[0038] In order to solve the above technical problems, the present application also provides a monitoring device for a substation, comprising:

[0039] An acquisition module, used for acquiring a three-dimensional static model established based on the ontological feature information of the substation automation equipment;

[0040] A first establishing module is used to establish an average association relationship model according to the resource information of the substation automation equipment;

[0041] A second establishing module is used to establish a topology model according to the three-dimensional static model and the resource information of the substation automation equipment;

[0042] A generation module, used for integrating the average association relationship model and the topology model to obtain a twin model of a substation automation system;

[0043] The monitoring module is used to perform global status perception on the twin model of the substation automation system and obtain the real-time operating status and parameters of the substation automation equipment.

[0044] As an optional solution, in the monitoring device of the above-mentioned substation, the first establishing module includes:

[0045] An original data acquisition unit, used to obtain a multidimensional data set according to the resource information of the substation automation equipment;

[0046] A resampling unit, used for resampling the multidimensional data set multiple times to obtain a corresponding resampled data set;

[0047] An initial association relationship model establishing unit, used to establish an initial association relationship model corresponding to the resource information and the equipment factor according to each of the resampled data sets, wherein the equipment factor is a preset condition affecting the operation of the automation equipment;

[0048] An average processing unit, used for averaging each of the initial association relationship models to obtain an average initial association relationship model between the resource information of the current substation automation equipment and the equipment factors;

[0049] A partitioning unit, configured to partition each of the resampled data sets according to the substation automation equipment probability value in the average initial association relationship model to obtain a partitioned data set;

[0050] A partition association relationship model establishing unit, used to establish a partition association relationship model corresponding to the resource information and the device factor according to each of the partition data sets;

[0051] The average association relationship model establishing unit is used to average the multiple partition association relationship models to obtain the average association relationship model corresponding to the resource information of the current substation automation equipment and the equipment factors.

[0052] As an optional solution, the monitoring device of the above substation further includes:

[0053] A judgment module, used to judge whether the average association relationship model is accurate according to a preset accuracy evaluation; if accurate, the output module is triggered; if inaccurate, the update unit is triggered;

[0054] The output module is used to output the current average association relationship model;

[0055] The updating unit is used to update the current average association relationship model to an average initial association relationship model, return to the step of dividing each of the resampled data sets according to the probability value of the substation automation equipment in the average initial association relationship model, and obtain the divided data sets until the average association relationship model is judged to be accurate according to a preset accuracy evaluation.

[0056] As an optional solution, in the monitoring device of the above-mentioned substation, the judgment module includes:

[0057] A validity judgment unit, used to judge whether the first formula is valid; if the first formula is valid, the accurate determination unit is triggered; if the first formula is not valid, the inaccurate determination unit is triggered;

[0058] The first formula is: (FC-CS) / 2 k ≤threshold;

[0059] Wherein, FC represents the data set of the average association relationship model; CS represents the data set of the average initial association relationship model; threshold represents the set threshold; k represents the number of states of the device factor of the automation device; 2 k Indicates the number of combinations of the resource information and the device factors;

[0060] The accuracy determination unit is used to determine that the average association relationship model is accurate;

[0061] The inaccurate determination unit is used to determine that the average association relationship model is inaccurate.

[0062] As an optional solution, in the monitoring device of the above-mentioned substation, the initial association relationship model establishing unit includes:

[0063] A resampled data set training subunit, used to input the resource information in the resampled data set and the combination of the preset device factors as test data into a neural network for training to obtain a corresponding model output result;

[0064] The initial association relationship model output subunit is used to use the model output result as the initial association relationship model.

[0065] As an optional solution, in the monitoring device of the above-mentioned substation, the partition association relationship model establishment unit includes:

[0066] A partition data input subunit, used for inputting the resource information in the partition data set and the combination of the preset device factors as test data into a neural network for training to obtain a corresponding model output result;

[0067] The partition association relationship model output subunit is used to use the model training result as the partition association relationship model.

[0068] In order to solve the above technical problems, the present application also provides a monitoring device for a substation, comprising:

[0069] Memory for storing computer programs;

[0070] The processor is used to implement the steps of the above-mentioned substation monitoring method when executing the computer program.

[0071] In order to solve the above technical problems, 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 steps of the above-mentioned substation monitoring method are implemented.

[0072] The monitoring method of the substation provided in the present application obtains a three-dimensional static model based on the ontological feature information of the substation automation equipment; establishes an average association relationship model according to the resource information of the substation automation equipment; establishes a topological model according to the three-dimensional static model and the resource information of the substation automation equipment; obtains the substation automation system twin model according to the average association relationship model and the topological model; performs global state perception on the substation automation system twin model to obtain the real-time operating status and parameters of the substation automation equipment. By establishing a three-dimensional static model based on the ontological features of the equipment, the structure and appearance of the equipment can be more intuitively understood. By establishing an average association relationship model, the operating status and performance of the equipment can be predicted and evaluated, and the topological model can describe the connection and interaction between the equipment. Through twin modeling, the operating status of the equipment can be monitored in real time, future performance changes can be predicted, and system optimization and troubleshooting can be performed. It provides a more comprehensive, accurate and real-time monitoring and management capability for the substation automation system. This helps to improve the efficiency and reliability of the system, reduce failures and maintenance costs, and enhance the stability and reliability of power supply.

[0073] In addition, the present application also provides a device and a medium, which correspond to the above-mentioned substation monitoring method and have the same effect as above. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] In order to more clearly illustrate the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. 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 any creative work.

[0075] Figure 1 A flow chart of a substation monitoring method is provided for an embodiment of the present application;

[0076] Figure 2 A structural diagram of a monitoring device for a substation provided in an embodiment of the present application;

[0077] Figure 3 A structural diagram of another substation monitoring device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0078] 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.

[0079] The core of this application is to provide a monitoring method, device and medium for a substation.

[0080] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0081] Electric energy is indispensable as the lifeblood of today's normal social life. Substation is a power facility that transforms voltage, receives and distributes electric energy, controls the flow of electricity and adjusts voltage in the power system. It connects power grids of various voltage levels through transformers. The main equipment of substations include transformers, circuit breakers, disconnectors, current transformers, voltage transformers, etc. According to the scale, substations can be divided into large, medium and small, and according to the structure, they can be divided into outdoor substations and indoor substations.

[0082] With the rapid development of computer technology, digital twins have become the core and key to the implementation of the Industrial Internet. Digital twins refer to the integration of multidisciplinary and multi-scale simulation processes by making full use of physical models, sensor data, operation history and other data. Through three-dimensional visualization, computer virtual model information can be used to reflect the entire life cycle of real physical equipment. In simple terms, it is an equivalent mapping of the physical world in the information world, making it possible to make changes that cannot be observed or are difficult to observe.

[0083] At present, digital twin technology has not been applied to the debugging and operation and maintenance of automation equipment, which makes it difficult to achieve accurate matching between the digital twin of the automation equipment system and the physical entity in actual operation.

[0084] In order to solve the above problem, this embodiment provides a monitoring method for a substation. Figure 1 A flow chart of a substation monitoring method is provided for an embodiment of the present application, such as Figure 1 As shown, including:

[0085] S11: Acquire a three-dimensional static model established based on the ontological feature information of the substation automation equipment;

[0086] S12: establishing an average association relationship model based on resource information of substation automation equipment;

[0087] S13: establishing a topology model based on the three-dimensional static model and resource information of the substation automation equipment;

[0088] S14: Integrate the average association relationship model and the topology model to obtain a twin model of the substation automation system;

[0089] S15: Perform global status perception on the twin model of the substation automation system to obtain the real-time operating status and parameters of the substation automation equipment.

[0090] Step S11: The three-dimensional static model established based on the characteristic information of the substation automation equipment refers to the use of information from various sources, such as equipment drawings, technical specifications, operating data, etc., to establish the appearance, structure and function model of the equipment. This can provide an accurate representation of the appearance and size of the equipment and can be used for subsequent analysis and simulation. The established model is a three-dimensional static modeling based on the characteristic information of the automation equipment, mainly for generating a three-dimensional model of the automation equipment. The focus of this model is on the appearance and structure of the equipment, and the purpose is to provide an accurate representation of the appearance and size of a device. This model is mainly used in scenarios such as equipment design, planning and visualization.

[0091] Specifically, a three-dimensional static model is established based on the ontological characteristic information of substation automation equipment: based on the substation system configuration description (SCD) file and the substation physical configuration description (SPCD) file, a complete three-dimensional static model library of automation equipment objects is established, including establishing a general three-dimensional model library for automation equipment, and uniquely identifying each three-dimensional static model of automation equipment through effective management of the three-dimensional static model library of automation equipment objects; describing in detail various parameters and attributes of the equipment; defining the format and specification of the three-dimensional static model configuration file of the automation equipment; realizing information interaction with the three-dimensional static model of the equipment by reading and parsing the configuration file; and the three-dimensional static model can be modified and updated through the configuration file to realize remote control and adjustment.

[0092] Through the connection between the 3D model of the automation equipment object in the control cloud and the DL / T860 model, the mapping relationship between the control cloud and the automation equipment is automatically generated, and the existing equipment manufacturer data, model data, equipment U position data, starting U position and other data on the cloud are fully utilized for 3D static model processing. Through the lightweight and highly reusable conversion components of the digital handover model, the 3D static model is lightweight processed in different application scenarios.

[0093] Steps S12 and S13 first use the multivariate information of the substation automation system, including equipment status, communication protocols, control logic, etc., to establish topological models of each application layer and business layer. These models will reflect the logical relationship and communication mechanism between devices, which will help understand the overall structure and operation mode of the system. The second is to model the substation automation equipment resources based on the multivariate information to obtain an average model of the relationship between these resources. This includes using various information to describe the performance, function, logical changes, etc. of the automation equipment resources in order to better understand the relationship between them.

[0094] Specifically, by combining the technical specifications of the new generation of autonomous and controllable substation automation equipment with existing simulation modeling technology, the business function simulation model of the automation equipment and the logic and output parameter changes of the automation equipment are realized, and the association between the substation automation equipment and related automation equipment resource information models of the digital twin system is realized.

[0095] Step S14 combines the average association model with the topology model to construct a twin model of the substation automation system, which can provide a model that reflects the equipment operation status and system behavior in real time, and is used for equipment operation monitoring, fault prediction and system optimization.

[0096] The purpose is to establish a twin model corresponding to the actual substation automation system to achieve real-time monitoring and prediction of equipment status. The model not only considers the appearance and structure of the equipment, but also considers the equipment's operating status, association relationship, topology and other information. This model is mainly used in scenarios such as equipment operation monitoring, fault diagnosis and remote control.

[0097] Step S15 performs three-dimensional global state perception on the twin model of the substation automation system. In this step, the twin model of the substation automation system will be globally perceived to obtain the real-time operating status and parameters of the equipment. In this way, the operating status of the equipment can be monitored in real time and used for fault prediction and early warning. Finally, it also includes uniquely identifying the three-dimensional model of the automation equipment, setting descriptions, and defining the format of the three-dimensional model configuration file of the automation equipment. In this step, each three-dimensional model of the automation equipment will be uniquely identified, and the various parameters and properties of the equipment will be described in detail. At the same time, the format and specifications of the three-dimensional model configuration file of the automation equipment are defined. In this way, information interaction with the three-dimensional model of the equipment can be achieved, and the three-dimensional model of the equipment can be modified and updated through the configuration file to achieve remote control and adjustment.

[0098] Through the monitoring method of the substation in the embodiment of the present application, a three-dimensional static model based on the feature information of the body of the substation automation equipment is obtained; an average association relationship model is established according to the resource information of the substation automation equipment; a topology model is established according to the three-dimensional static model and the resource information of the substation automation equipment; a substation automation system twin model is obtained according to the average association relationship model and the topology model; the substation automation system twin model is globally perceived to obtain the real-time operating status and parameters of the substation automation equipment. By establishing a three-dimensional static model based on the body characteristics of the equipment, the structure and appearance of the equipment can be more intuitively understood. By establishing an average association relationship model, the operating status and performance of the equipment can be predicted and evaluated, and the topology model can describe the connection and interaction between the equipment. Through twin modeling, the operating status of the equipment can be monitored in real time, future performance changes can be predicted, and system optimization and troubleshooting can be performed. It provides a more comprehensive, accurate and real-time monitoring and management capability for the substation automation system. This helps to improve the efficiency and reliability of the system, reduce failures and maintenance costs, and enhance the stability and reliability of power supply.

[0099] According to the above embodiment, in a specific implementation scheme, the substation monitoring method, wherein the average association relationship model is established according to the resource information of the substation automation equipment, comprises:

[0100] Obtaining a multidimensional data set according to the resource information of the substation automation equipment;

[0101] Resampling the multidimensional data set multiple times to obtain corresponding resampled data sets;

[0102] Establishing an initial association relationship model corresponding to the resource information and the equipment factor according to each of the resampled data sets, wherein the equipment factor is a preset condition affecting the operation of the automation equipment;

[0103] After averaging the initial association relationship models, an average initial association relationship model between the resource information of the current substation automation equipment and the equipment factors is obtained;

[0104] According to the substation automation equipment probability value in the average initial association relationship model, each of the resampled data sets is divided to obtain a divided data set;

[0105] Establishing a partition association relationship model corresponding to the resource information and the device factors according to each of the partition data sets;

[0106] After averaging the plurality of partition association relationship models, the average association relationship model corresponding to the resource information of the current substation automation equipment and the equipment factors is obtained.

[0107] According to the description, the resource information of the substation automation equipment obtains a multidimensional data set, and it is necessary to generate a data set according to the actual information type, such as the equipment manufacturer data, model data, equipment U number data, and starting U position data set of L×Y×A×B. The equipment manufacturer data, model data, equipment U number data, and starting U position data set belong to the resource information.

[0108] Resample the multidimensional dataset multiple times (a times) to obtain the corresponding resampled datasets (a); each resampling will randomly select a certain number of samples from the original dataset, thus generating a resampled datasets H of the same size i , i=1,2,3…a.

[0109] For the resampled dataset H i , establish the initial association relationship model CS of the resource information of substation automation equipment and related equipment factors using the resampled data set as training data i ; where i =

[0110] 1, 2, 3 ... a; The equipment factors mentioned in this embodiment refer to the parameters or condition factors of the automation equipment of the substation during operation, and an average correlation relationship model between resource information and equipment factors is established.

[0111] Averaging the results of a modeling on the current substation automation equipment factors to obtain an average initial correlation relationship model CS between the resource information of the current substation automation equipment and the equipment factors;

[0112]

[0113] For the i-th resampled data set H i According to the probability value of substation automation equipment in the average initial association relationship model CS, the sample data set is divided to obtain the divided data set F i ; Establish the division correlation model FC of substation automation equipment factors and related automation equipment resource information after the current division i ;

[0114] Using the divided data set, the results of a modeling on the current substation automation equipment factors are averaged to obtain the average correlation relationship model FC between the substation automation equipment factors and the related automation equipment resource information after division;

[0115]

[0116] Through random resampling with replacement, a resampled data set of the same size is generated. This increases the diversity of the data and the generalization ability of the model, because each resampled data set may contain different samples and distribution characteristics. Through resampling, initial model establishment, model averaging, data set partitioning and re-model averaging, the accuracy and stability of the correlation model between substation automation equipment factors and related resource information are improved, the monitoring and management capabilities of the system are enhanced, and the reliability and stability of power supply are improved.

[0117] According to the above embodiment, in a specific implementation scheme, the monitoring method of the substation, after averaging the divided association relationship model to obtain the average association relationship model, further includes:

[0118] Determining whether the average association relationship model is accurate according to a preset accuracy assessment;

[0119] If it is accurate, then the current average correlation model is output;

[0120] If it is inaccurate, the current average association relationship model is updated to the average initial association relationship model, and the step of returning to the step of dividing each of the resampled data sets according to the probability value of the substation automation equipment in the average initial association relationship model to obtain the divided data set is performed until the average association relationship model is judged to be accurate according to the preset accuracy evaluation.

[0121] The randomness and uncertainty of the data are taken into account, which improves the accuracy and robustness of the model.

[0122] Specifically, judging whether the average association relationship model is accurate according to a preset accuracy evaluation includes:

[0123] Determine whether the first formula is valid;

[0124] The first formula is: (FC-CS) / 2 k ≤threshold;

[0125] Wherein, FC represents the data set of the average association relationship model; CS represents the data set of the average initial association relationship model; threshold represents the set threshold; k represents the number of states of the device factor of the automation device; 2 k Indicates the number of combinations of the resource information and the device factors;

[0126] If the first formula is established, it is determined that the average correlation relationship model is accurate;

[0127] If the first formula is not valid, it is determined that the average association relationship model is inaccurate.

[0128] The average association relationship model and the average initial association relationship model established in the above embodiments are models of a data set type, and subtraction operations can be performed between data sets.

[0129] When judging whether the process is accurate, a comparison between the change value and the threshold is introduced. When the change value does not exceed the threshold, the process is considered accurate. This method can quantitatively evaluate the stability and accuracy of the model and provide a basis for the final determination of the model. For example, the threshold is set to 0.02.

[0130] k represents the number of states of the substation automation equipment factors. Specifically, assuming there are k factors, each of which has two states (whether the equipment is turned on or off), the total number of state combinations is 2. k .

[0131] When the process is inaccurate, the current FC value is used to update CS. This iterative update method can gradually optimize the model to make it closer to the actual situation. Through continuous iteration and adjustment, the model will gradually converge, thereby improving its accuracy and stability.

[0132] Since the process is carried out for each substation automation equipment factor separately, when a new device or factor is added, it is only necessary to repeat the above process for the new device or factor to incorporate it into the model. This makes the model highly scalable and can adapt to substation automation systems of different sizes and complexities.

[0133] According to the above embodiment, in a specific implementation scheme, the monitoring method of the substation establishes an initial association relationship model corresponding to the resource information and the equipment factors according to each of the resampled data sets, including:

[0134] Inputting the resource information in the resampled data set and the combination of the preset device factors into a neural network as test data for training to obtain a corresponding model output result;

[0135] The model output result is used as the initial association relationship model.

[0136] The current substation automation equipment factors k Each E in the state combination i As the test data input model, record the output of the model's initial association relationship model S ij , j = 1, 2…2 k , then after averaging the initial correlation relationship models, the average initial correlation relationship model between the resource information of the current substation automation equipment and the equipment factors is obtained as CS i =(S i1,S i2 …S ij ).

[0137] According to the above embodiment, in a specific implementation scheme, the monitoring method of the substation establishes a partition association relationship model corresponding to the resource information and the equipment factors according to each of the partition data sets, including:

[0138] Inputting the resource information in the divided data set and the combination of the preset device factors into a neural network as test data for training to obtain a corresponding model output result;

[0139] The model training result is used as the partition association relationship model.

[0140] Use the i-th partition data set F i The following steps are used to establish the correlation model FC between the substation automation equipment factors and the related automation equipment resource information after the current division: i :2 of the current substation automation equipment factors k Each E in the state combination i As the test data input model, record the output of the model and divide the associated relationship model F ij After averaging the multiple partition association relationship models, the average association relationship model FC corresponding to the resource information of the current substation automation equipment and the equipment factor is obtained; i =(F i1 ,F i2 …F ij ).

[0141] The sample data set is divided according to the device probability value in the average initial association relationship model, and the association relationship model is established. This division method can make the model better adapt to different data distributions and scenarios, and improve the adaptability and generalization ability of the model.

[0142] According to the above embodiment, in a specific implementation scheme, the monitoring method of the substation, the global state perception of the substation automation system twin model is performed to obtain the real-time operating status and parameters of the substation automation equipment, and then further includes:

[0143] The real-time operating status and parameters are displayed on a human-computer interaction interface.

[0144] Image recognition technology is used to intelligently identify secondary physical wiring in existing automation system drawings, and the three-dimensional model of automation equipment obtained after integrating it into the twin modeling of the substation automation system is visualized and applied, expanding the application space of the three-dimensional model of automation equipment and supporting the development of subsequent application business.

[0145] In the above embodiments, the monitoring method of the substation is described in detail, and the present application also provides a corresponding embodiment of the monitoring device of the substation. It should be noted that the present application describes the embodiments of the device part from two perspectives, one is based on the perspective of the functional module, and the other is based on the perspective of the hardware.

[0146] From the perspective of functional modules, Figure 2 A structural diagram of a monitoring device for a substation provided in an embodiment of the present application, such as Figure 2 As shown, the monitoring device of the substation includes:

[0147] An acquisition module 21 is used to acquire a three-dimensional static model established based on the entity feature information of the substation automation equipment;

[0148] A first establishing module 22, used to establish an average association relationship model according to the resource information of the substation automation equipment;

[0149] A second establishing module 23, configured to establish a topology model according to the three-dimensional static model and resource information of the substation automation equipment;

[0150] A generating module 24, configured to integrate the average association relationship model and the topology model to obtain a twin model of a substation automation system;

[0151] The monitoring module 25 is used to perform global status perception on the substation automation system twin model and obtain the real-time operating status and parameters of the substation automation equipment.

[0152] The first establishment module includes:

[0153] An original data acquisition unit, used to obtain a multidimensional data set according to the resource information of the substation automation equipment;

[0154] A resampling unit, used for resampling the multidimensional data set multiple times to obtain a corresponding resampled data set;

[0155] An initial association relationship model establishing unit, used to establish an initial association relationship model corresponding to the resource information and the equipment factor according to each of the resampled data sets, wherein the equipment factor is a preset condition affecting the operation of the automation equipment;

[0156] An average processing unit, used for averaging each of the initial association relationship models to obtain an average initial association relationship model between the resource information of the current substation automation equipment and the equipment factors;

[0157] A partitioning unit, configured to partition each of the resampled data sets according to the substation automation equipment probability value in the average initial association relationship model to obtain a partitioned data set;

[0158] A partition association relationship model establishing unit, used to establish a partition association relationship model corresponding to the resource information and the device factor according to each of the partition data sets;

[0159] The average association relationship model establishing unit is used to average the multiple partition association relationship models to obtain the average association relationship model corresponding to the resource information of the current substation automation equipment and the equipment factors.

[0160] Also includes:

[0161] A judgment module, used to judge whether the average association relationship model is accurate according to a preset accuracy evaluation; if accurate, the output module is triggered; if inaccurate, the update unit is triggered;

[0162] The output module is used to output the current average association relationship model;

[0163] An updating unit is used to update the current average association relationship model to an average initial association relationship model, return to the step of dividing each of the resampled data sets according to the probability value of the substation automation equipment in the average initial association relationship model, and obtain the divided data sets until the average association relationship model is judged to be accurate according to a preset accuracy evaluation.

[0164] The judging module comprises:

[0165] A validity judgment unit, used to judge whether the first formula is valid; if the first formula is valid, the accurate determination unit is triggered; if the first formula is not valid, the inaccurate determination unit is triggered;

[0166] The first formula is: (FC-CS) / 2 k ≤threshold;

[0167] Wherein, FC represents the data set of the average association relationship model; CS represents the data set of the average initial association relationship model; threshold represents the set threshold; k represents the number of states of the device factor of the automation device; 2 k Indicates the number of combinations of the resource information and the device factors;

[0168] The accuracy determination unit is used to determine that the average association relationship model is accurate;

[0169] The inaccurate determination unit is used to determine that the average association relationship model is inaccurate.

[0170] The initial association relationship model establishing unit includes:

[0171] A resampled data set training subunit, used to input the resource information in the resampled data set and the combination of the preset device factors as test data into a neural network for training to obtain a corresponding model output result;

[0172] The initial association relationship model output subunit is used to use the model output result as the initial association relationship model.

[0173] The partition association relationship model establishment unit includes:

[0174] A partition data input subunit, used for inputting the resource information in the partition data set and the combination of the preset device factors as test data into a neural network for training to obtain a corresponding model output result;

[0175] The partition association relationship model output subunit is used to use the model training result as the partition association relationship model.

[0176] The display module is used to display the real-time operating status and parameters on the human-computer interaction interface.

[0177] Since the embodiments of the apparatus part correspond to the embodiments of the method part, please refer to the description of the embodiments of the method part for the embodiments of the apparatus part, which will not be repeated here.

[0178] Figure 3 A structural diagram of another substation monitoring device provided in an embodiment of the present application, such as Figure 3 As shown, the monitoring device of the substation includes: a memory 30 for storing a computer program;

[0179] The processor 31 is used to implement the steps of the method for obtaining user operation habit information in the above embodiment (substation monitoring method) when executing the computer program.

[0180] The monitoring device for the substation provided in this embodiment may include but is not limited to a smart phone, a tablet computer, a laptop computer or a desktop computer.

[0181] Among them, the processor 31 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 31 can be implemented in at least one hardware form of a digital signal processor (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 31 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a central processing unit (CPU); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 31 may be integrated with a graphics processing unit (GPU), and the GPU is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 31 may also include an artificial intelligence (AI) processor, which is used to process computing operations related to machine learning.

[0182] The memory 30 may include one or more computer-readable storage media, which may be non-transitory. The memory 30 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In this embodiment, the memory 30 is at least used to store the following computer program 301, wherein, after the computer program is loaded and executed by the processor 31, it can implement the relevant steps of the substation monitoring method disclosed in any of the aforementioned embodiments. In addition, the resources stored in the memory 30 may also include an operating system 302 and data 303, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system 302 may include Windows, Unix, Linux, etc. Data 303 may include but is not limited to data involved in implementing the substation monitoring method, etc.

[0183] In some embodiments, the monitoring device of the substation may further include a display screen 32 , an input / output interface 33 , a communication interface 34 , a power supply 35 , and a communication bus 36 .

[0184] Those skilled in the art will understand that Figure 3 The structure shown in the figure does not constitute a limitation on the monitoring device of the substation, and may include more or less components than those shown in the figure.

[0185] The monitoring device for a substation provided in an embodiment of the present application includes a memory and a processor. When the processor executes a program stored in the memory, it can implement the following method: a monitoring method for a substation.

[0186] Finally, the present application also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps described in the above-mentioned embodiment of the monitoring method for a substation are implemented.

[0187] It is understandable that if the method in the above embodiment is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0188] The computer-readable storage medium provided in this embodiment stores a computer program, and when a processor executes the program, the following method can be implemented: a monitoring method for a substation.

[0189] The above is a detailed introduction to the monitoring method, device and medium for the substation provided by the present application. The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the embodiments can be referenced to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the scope of protection of the claims of the present application.

[0190] It should also be noted that, in this specification, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

Claims

1. A monitoring method for a substation, characterized in that: include: Obtain a three-dimensional static model based on the ontological feature information of the substation automation equipment; Establishing an average association relationship model according to the resource information of the substation automation equipment; Establishing a topology model according to the three-dimensional static model and resource information of the substation automation equipment; Integrating the average association relationship model and the topology model to obtain a twin model of a substation automation system; Performing global state perception on the substation automation system twin model to obtain the real-time operating status and parameters of the substation automation equipment; Wherein, establishing an average association relationship model according to the resource information of the substation automation equipment includes: Obtaining a multidimensional data set according to the resource information of the substation automation equipment; Resampling the multidimensional data set multiple times to obtain corresponding resampled data sets; Establishing an initial association relationship model corresponding to the resource information and the equipment factor according to each of the resampled data sets, wherein the equipment factor is a preset condition affecting the operation of the automation equipment; After averaging the initial association relationship models, an average initial association relationship model between the resource information of the current substation automation equipment and the equipment factors is obtained; According to the substation automation equipment probability value in the average initial association relationship model, each of the resampled data sets is divided to obtain a divided data set; Establishing a partition association relationship model corresponding to the resource information and the device factors according to each of the partition data sets; After averaging the plurality of partition association relationship models, the average association relationship model corresponding to the resource information of the current substation automation equipment and the equipment factors is obtained.

2. The monitoring method of a substation according to claim 1, characterized in that: After averaging the plurality of divided association relationship models, the average association relationship model corresponding to the resource information of the current substation automation equipment and the equipment factor is obtained, and then the following further includes: Determining whether the average association relationship model is accurate according to a preset accuracy assessment; If it is accurate, then the current average correlation model is output; If it is inaccurate, the current average association relationship model is updated to the average initial association relationship model, and the step of returning to the step of dividing each of the resampled data sets according to the probability value of the substation automation equipment in the average initial association relationship model to obtain the divided data set is performed until the average association relationship model is judged to be accurate according to the preset accuracy evaluation.

3. The monitoring method of a substation according to claim 2, characterized in that: The step of judging whether the average association relationship model is accurate according to a preset accuracy evaluation includes: Determine whether the first formula is valid; The first formula is: (FC-CS) / 2k≤threshold; Wherein, FC represents the data set of the average association relationship model; CS represents the data set of the average initial association relationship model; threshold represents the set threshold; k represents the number of states of the device factor of the automation device; 2k represents the number of combinations of the resource information and the device factor; If the first formula is established, it is determined that the average correlation relationship model is accurate; If the first formula is not valid, it is determined that the average association relationship model is inaccurate.

4. The monitoring method of a substation according to claim 3, characterized in that: The step of establishing an initial association relationship model corresponding to the resource information and the device factors according to each of the resampled data sets includes: Inputting the resource information in the resampled data set and the combination of the preset device factors into a neural network as test data for training to obtain a corresponding model output result; The model output result is used as the initial association relationship model.

5. The monitoring method of a substation according to claim 3, characterized in that: The step of establishing a partition association relationship model corresponding to the resource information and the device factors according to each of the partition data sets includes: Inputting the resource information in the divided data set and the combination of the preset device factors into a neural network as test data for training to obtain a corresponding model output result; The model training result is used as the partition association relationship model.

6. The monitoring method of a substation according to claim 1, characterized in that: Performing global state perception on the substation automation system twin model to obtain the real-time operating status and parameters of the substation automation equipment, and then further comprising: The real-time operating status and parameters are displayed on a human-computer interaction interface.

7. A monitoring device for a substation, characterized in that: include: An acquisition module, used for acquiring a three-dimensional static model established based on the ontological feature information of the substation automation equipment; A first establishing module is used to establish an average association relationship model according to the resource information of the substation automation equipment; A second establishing module is used to establish a topology model according to the three-dimensional static model and the resource information of the substation automation equipment; A generation module, used for integrating the average association relationship model and the topology model to obtain a twin model of a substation automation system; A monitoring module is used to perform global state perception on the substation automation system twin model and obtain the real-time operating status and parameters of the substation automation equipment; The first establishment module comprises: An original data acquisition unit, used to obtain a multidimensional data set according to the resource information of the substation automation equipment; A resampling unit, used for resampling the multidimensional data set multiple times to obtain a corresponding resampled data set; An initial association relationship model establishing unit, used to establish an initial association relationship model corresponding to the resource information and the equipment factor according to each of the resampled data sets, wherein the equipment factor is a preset condition affecting the operation of the automation equipment; An average processing unit, used for averaging each of the initial association relationship models to obtain an average initial association relationship model between the resource information of the current substation automation equipment and the equipment factors; A partitioning unit, configured to partition each of the resampled data sets according to the substation automation equipment probability value in the average initial association relationship model to obtain a partitioned data set; A partition association relationship model establishing unit, used to establish a partition association relationship model corresponding to the resource information and the device factor according to each of the partition data sets; The average association relationship model establishing unit is used to average the multiple partition association relationship models to obtain the average association relationship model corresponding to the resource information of the current substation automation equipment and the equipment factors.

8. The monitoring device for a substation according to claim 7, characterized in that: Also includes: A judgment module, used to judge whether the average association relationship model is accurate according to a preset accuracy evaluation; If it is accurate, the output module is triggered; If it is inaccurate, the update unit is triggered; The output module is used to output the current average association relationship model; An updating unit is used to update the current average association relationship model to an average initial association relationship model, return to the step of dividing each of the resampled data sets according to the probability value of the substation automation equipment in the average initial association relationship model, and obtain the divided data sets until the average association relationship model is judged to be accurate according to a preset accuracy evaluation.

9. The monitoring device for a substation according to claim 8, characterized in that: The judging module comprises: A validity judgment unit, used to judge whether the first formula is valid; if the first formula is valid, the accurate determination unit is triggered; if the first formula is not valid, the inaccurate determination unit is triggered; The first formula is: (FC-CS) / 2k≤threshold; Wherein, FC represents the data set of the average association relationship model; CS represents the data set of the average initial association relationship model; threshold represents the set threshold; k represents the number of states of the device factor of the automation device; 2k represents the number of combinations of the resource information and the device factor; The accuracy determination unit is used to determine that the average association relationship model is accurate; The inaccurate determination unit is used to determine that the average association relationship model is inaccurate.

10. The monitoring device for a substation according to claim 9, characterized in that: The initial association relationship model establishing unit includes: A resampled data set training subunit, used to input the resource information in the resampled data set and the combination of the preset device factors as test data into a neural network for training to obtain a corresponding model output result; The initial association relationship model output subunit is used to use the model output result as the initial association relationship model.

11. The monitoring device for a substation according to claim 10, characterized in that: The partition association relationship model establishment unit includes: A partition data input subunit, used for inputting the resource information in the partition data set and the combination of the preset device factors into the neural network as test data for training to obtain a corresponding model output result; The partition association relationship model output subunit is used to use the model training result as the partition association relationship model.

12. A monitoring device for a substation, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the substation monitoring method as described in any one of claims 1 to 6 when executing the computer program.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the substation monitoring method according to any one of claims 1 to 6 are implemented.

Images