An electronic voltage transformer status recognition method and system under limited samples

Abstract

The present invention relates to a method and system for identifying the state of an electronic voltage transformer under limited samples. The method includes the following steps: collecting the operation data of the electronic voltage transformer and preprocessing the operation data; creating an initial feature set based on the operation data, setting a feature combination strategy to recombine the initial feature set to obtain a fused feature set; constructing an operation data sample expansion model, training the operation data sample expansion model based on the fused feature set, expanding the operation data through the trained operation data sample expansion model to obtain an operation data expanded sample set; constructing an electronic voltage transformer state identification model, adaptively adjusting the parameters of the electronic voltage transformer state identification model based on the line topology features; applying the adaptively adjusted parameters to the electronic voltage transformer state identification model, and identifying the state of the electronic voltage transformer through the operation data expanded sample set.

Description

Technical Field

[0001] The present invention relates to a method and system for identifying the state of an electronic voltage transformer under limited samples, belonging to the technical field of power metering misalignment identification. Background Art

[0002] An electronic voltage transformer (EVT) is one of the key devices in modern power systems and is used to measure the voltage of high-voltage transmission lines. Compared with traditional electromagnetic voltage transformers, EVTs have the advantages of small size, light weight, fast response speed, and no ferromagnetic resonance, and are widely used in smart grids, substation automation and other fields. The normal operation of EVTs is crucial for the safety and stability of power systems, so real-time monitoring and fault diagnosis of their states are of great significance.

[0003] In actual operation, the abnormal conditions of EVTs may be rare, and the abnormal signals may be very close to the normal signals and difficult to distinguish. In many cases, only data in the normal operation state can be obtained, lacking abnormal samples, which makes it difficult to apply traditional supervised learning methods. Summary of the Invention

[0004] To solve the problems existing in the above-mentioned prior art, the present invention proposes a method and system for identifying the state of an electronic voltage transformer under limited samples.

[0005] The technical solution of the present invention is as follows:

[0006] On the one hand, the present invention provides a method for identifying the state of an electronic voltage transformer under limited samples, including the following steps:

[0007] Collect the operation data of the electronic voltage transformer and preprocess the operation data;

[0008] Create an initial feature set based on the preprocessed operation data, set a feature combination strategy to recombine the initial feature set, and obtain a fused feature set;

[0009] Construct an operation data sample augmentation model, train the operation data sample augmentation model based on the fused feature set, and augment the operation data through the trained operation data sample augmentation model to obtain an operation data augmented sample set;

[0010] Construct an electronic voltage transformer state recognition model based on the DBSCAN algorithm, and adaptively adjust the parameters of the electronic voltage transformer state recognition model based on the line topology features of the electronic voltage transformer;

[0011] Apply the adaptive adjustment parameters to the electronic voltage transformer status recognition model, and identify the status of the electronic voltage transformer through the operation data to expand the sample set.

[0012] Preferably, the operation data of the electronic voltage transformer includes voltage waveform, current waveform, temperature, and humidity;

[0013] Perform normalization processing on the operation data, as shown in the following formula:

[0014] ;

[0015] Where: represents the collected operation data; represents the mean value of the operation data; represents the standard deviation of the operation data; represents the normalized operation data.

[0016] Preferably, create an initial feature set based on the preprocessed operation data, and the initial feature set includes the mean value, variance, skewness, kurtosis, waveform factor, and kurtosis index of the preprocessed operation data.

[0017] Preferably, the operation data sample expansion model is constructed based on the GAN model.

[0018] Preferably, set a feature combination strategy to recombine the initial feature set to obtain a fused feature set, specifically:

[0019] For each feature sample in the initial feature set, calculate its influence on the output of the operation data sample expansion model, as shown in the following formula:

[0020] ;

[0021] Where: represents the operation data sample expansion model function; represents the initial feature set; represents the th feature sample in the initial feature set; represents the th influence amount of the feature sample;

[0022] Normalize the influence amounts of all feature samples, and calculate the weight of each feature sample and perform non-linear transformation based on the normalized influence amounts of the feature samples, as shown in the following formula:

[0023] ;

[0024] Where: represents the weight of the th feature sample; denotes the th feature sample after normalization; denotes the th feature sample after normalization; denotes the natural constant;

[0025] Each feature sample is weighted and fused with its corresponding weight to obtain a fused feature set.

[0026] Preferably, the fused feature set is introduced as conditional information into the discriminator of the GAN model, as shown in the following formula:

[0027] ;

[0028] Where: denotes the discriminator function; denotes the fused feature set; denotes the true / false label;

[0029] During the training process, the initial feature set is used as the conditional vector, and at the same time, a random noise vector is created. The conditional vector and the random noise vector are input into the generator of the GAN model to generate samples, and then the discriminator is used to judge the true / false label of the generated samples. The loss is calculated according to the judgment accuracy, and then the parameters of the GAN model are updated based on the loss through the backpropagation algorithm.

[0030] Preferably, the specific steps for adaptively adjusting the parameters of the electronic voltage transformer status recognition model based on the line topology features of the electronic voltage transformer are as follows:

[0031] Construct a line topology feature map of the electronic voltage transformer based on the topology information of the electronic voltage transformer. Among them, each node of the graph represents an electronic voltage transformer, and each edge of the graph represents the connection status between the electronic voltage transformers;

[0032] For each node in the voltage transformer topology feature map, calculate its local density index, as shown in the following formula:

[0033] ;

[0034] Where: denotes the local density index of the th node; denotes the th node and its th nearest neighbor distance;

[0035] Calculate the topological weight of each node, as shown in the following formula:

[0036] ;

[0037] Where: represents the topological weight of the th node; represents the number of connections of the th node with other nodes; represents the total number of nodes; and respectively represent the importance coefficients of the current node degree and the total number of nodes;

[0038] Initialize the initial radius and the initial minimum number of samples of the DBSCAN algorithm;

[0039] For each node, adjust its minimum number of samples according to its topological weight, as shown in the following formula:

[0040] ;

[0041] where: represents the adjusted minimum number of samples of the th node; represents the initial minimum number of samples;

[0042] For each node, adjust its radius based on the local density index, as shown in the following formula:

[0043] ;

[0044] where: represents the adjusted radius of the th node; represents the initial radius; represents the average value of the local density index; represents the adjustment coefficient;

[0045] For each unvisited node of the DBSCAN algorithm, determine whether it is a core point. If it is a core point, start a new cluster and recursively expand the cluster;

[0046] Mark non-core points as border points, mark isolated points that cannot be expanded as noise points, and regard noise points as outliers.

[0047] On the other hand, the present invention also provides an electronic voltage transformer state recognition system under limited samples, including a data acquisition module, a feature fusion module, a sample expansion module, and a state recognition module;

[0048] The data acquisition module is used to collect the operation data of the electronic voltage transformer and preprocess the operation data;

[0049] The feature fusion module is used to create an initial feature set based on the preprocessed operation data, and set a feature combination strategy to recombine the initial feature set to obtain a fused feature set;

[0050] The sample augmentation module is used to construct an operation data sample augmentation model, train the operation data sample augmentation model based on the fused feature set, and augment the operation data through the trained operation data sample augmentation model to obtain an operation data augmented sample set;

[0051] The state recognition module is used to construct an electronic voltage transformer state recognition model based on the DBSCAN algorithm, and adaptively adjust the parameters of the electronic voltage transformer state recognition model based on the line topology features of the electronic voltage transformer; apply the adaptively adjusted parameters to the electronic voltage transformer state recognition model, and recognize the state of the electronic voltage transformer through the operation data augmented sample set.

[0052] On the other hand, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the method described in the present invention is implemented.

[0053] On the other hand, the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the method described in the present invention is implemented.

[0054] The present invention has the following beneficial effects:

[0055] 1. The present invention proposes a GAN algorithm improved based on the signal feature conditions of the transformer, and performs data expansion for the transformer data features, solving the problem of insufficient transformer data samples.

[0056] 2. The present invention proposes a DBSCAN classification algorithm for adaptive parameter adjustment based on the line topology structure, which can enhance the robustness and recognition accuracy of the algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a flowchart of the method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0058] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the protection scope of the present invention.

[0059] It should be understood that the step numbers used in the text are only for convenience of description and do not limit the order of execution of the steps.

[0060] It should be understood that the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0061] The terms "comprising" and "including" indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0062] The term " / or" refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0063] Embodiment 1:

[0064] See Figure 1 , a method for identifying the state of an electronic voltage transformer under limited samples, comprising the following steps:

[0065] Collect the operation data of the electronic voltage transformer (these data can come from multiple sensors, including voltage sensors, current sensors, temperature sensors, humidity sensors, etc., and the data are continuous time-series data, collecting data once per second. When collecting data, status information such as "normal" and "abnormal" can be marked for each data point. Although this method mainly focuses on normal data, in the subsequent verification and testing phases, the marked data can help evaluate the performance of the model), and preprocess the operation data;

[0066] Create an initial feature set based on the preprocessed operation data, set a feature combination strategy to recombine the initial feature set, and obtain a fused feature set;

[0067] Construct an operation data sample augmentation model, train the operation data sample augmentation model based on the fused feature set, and augment the operation data through the trained operation data sample augmentation model to obtain an operation data augmented sample set;

[0068] Construct a state identification model for the electronic voltage transformer based on the DBSCAN algorithm, and adaptively adjust the parameters of the state identification model for the electronic voltage transformer based on the line topology characteristics of the electronic voltage transformer;

[0069] Apply the adaptive adjustment parameters to the electronic voltage transformer status recognition model, and identify the status of the electronic voltage transformer through the operation data to expand the sample set.

[0070] As a preferred implementation manner of this embodiment, the operation data of the electronic voltage transformer includes voltage waveform, current waveform, temperature, and humidity;

[0071] Perform normalization processing on the operation data, as shown in the following formula:

[0072] ;

[0073] Where: represents the collected operation data; represents the mean value of the operation data; represents the standard deviation of the operation data; represents the operation data after normalization.

[0074] As a preferred implementation manner of this embodiment, create an initial feature set based on the preprocessed operation data. The initial feature set includes the mean value, variance, skewness, kurtosis, waveform factor, and kurtosis index of the preprocessed operation data; these features can provide different perspectives on the transformer status, but each of them may not be sufficient to comprehensively describe complex fault modes.

[0075] As a preferred implementation manner of this embodiment, the operation data sample expansion model is constructed based on the GAN model.

[0076] As a preferred implementation manner of this embodiment, set a feature combination strategy to recombine the initial feature set to obtain a fused feature set. Specifically:

[0077] For each feature sample in the initial feature set, calculate its influence on the output of the operation data sample expansion model, as shown in the following formula:

[0078] ;

[0079] Where: represents the operation data sample expansion model function; represents the initial feature set; represents the th feature sample in the initial feature set; represents the th influence amount of the feature sample;

[0080] Normalize the influence amounts of all feature samples (using methods such as min-max normalization or Z-score standardization), and calculate the weights of each feature sample based on the normalized influence amounts of the feature samples and perform non-linear transformation to ensure that the sum of the weights is 1, as shown in the following formula:

[0081] ;

[0082] Where: represents the weight of the th feature sample; represents the th feature sample after normalization; represents the th feature sample after normalization; represents the natural constant;

[0083] Fuse each feature sample with its corresponding weight to obtain a fused feature set.

[0084] As a preferred implementation manner of this embodiment, introduce the fused feature set as conditional information into the discriminator of the GAN model, as shown in the following formula:

[0085] ;

[0086] Where: represents the discriminator function; represents the fused feature set, , represents the total number of samples in the initial feature set; represents the true or false label;

[0087] The discriminator function is specifically shown in the following formula:

[0088] ;

[0089] During the training process, use the initial feature set as the conditional vector, and at the same time create a random noise vector. Input the conditional vector and the random noise vector into the generator of the GAN model to generate samples, and then use the discriminator to judge the true or false label of the generated samples. Calculate the loss according to the judgment accuracy, and then update the parameters of the GAN model based on the loss through the backpropagation algorithm.

[0090] As a preferred implementation manner of this embodiment, the specific steps for adaptively adjusting the parameters of the electronic voltage transformer status recognition model based on the line topology features of the electronic voltage transformer are as follows:

[0091] Construct an electronic voltage transformer line topology feature map based on the topology information of the electronic voltage transformer. Each node in the map represents an electronic voltage transformer, and each edge in the map represents the connection status between electronic voltage transformers;

[0092] For each node in the voltage transformer topology feature map, calculate its local density index, as shown in the following formula:

[0093] ;

[0094] Where: represents the local density index of the th node; represents the th node and its th nearest neighbor distance;

[0095] Calculate the topological weight of each node, as shown in the following formula:

[0096] ;

[0097] Where: represents the topological weight of the th node; represents the number of connections of the th node to other nodes; represents the total number of nodes; , respectively represent the importance coefficients of the current node degree and the total number of nodes;

[0098] Initialize the initial radius and the initial minimum number of samples of the DBSCAN algorithm;

[0099] For each node, adjust its minimum number of samples according to its topological weight, as shown in the following formula:

[0100] ;

[0101] Where: represents the adjusted minimum number of samples of the th node; represents the initial minimum number of samples;

[0102] For each node, adjust its radius based on the local density index, as shown in the following formula:

[0103] ;

[0104] Where: represents the adjusted radius of the th node; represents the initial radius; represents the average value of the local density index; represents the adjustment coefficient;

[0105] For each node not visited by the DBSCAN algorithm, determine whether it is a core point. If it is a core point, start a new cluster and recursively expand the cluster;

[0106] Mark non-core points as border points, mark isolated points that cannot be expanded as noise points, regard noise points as abnormal points, and determine the status of each electronic voltage transformer based on abnormal points and normal points.

[0107] Embodiment 2:

[0108] An electronic voltage transformer status recognition system under limited samples includes a data acquisition module, a feature fusion module, a sample expansion module, and a status recognition module;

[0109] The data acquisition module is used to collect the operation data of the electronic voltage transformer and preprocess the operation data;

[0110] The feature fusion module is used to create an initial feature set based on the preprocessed operation data, set a feature combination strategy to recombine the initial feature set, and obtain a fused feature set;

[0111] The sample expansion module is used to build an operation data sample expansion model, train the operation data sample expansion model based on the fused feature set, and expand the operation data through the trained operation data sample expansion model to obtain an operation data expanded sample set;

[0112] The status recognition module is used to build an electronic voltage transformer status recognition model based on the DBSCAN algorithm, adaptively adjust the parameters of the electronic voltage transformer status recognition model based on the line topology characteristics of the electronic voltage transformer; apply the adaptively adjusted parameters to the electronic voltage transformer status recognition model, and recognize the status of the electronic voltage transformer through the operation data expanded sample set.

[0113] This system is used to implement the method in Embodiment 1, which will not be elaborated here.

[0114] Embodiment 3:

[0115] This embodiment proposes an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the method described in any embodiment of the present invention.

[0116] Embodiment 4:

[0117] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the method described in any embodiment of the present invention is implemented.

[0118] In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent the case where A exists alone, A and B exist simultaneously, or B exists alone. Where A and B may be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one of the following" and its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, and c may represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c may be single or multiple.

[0119] Those of ordinary skill in the art can realize that the various units and algorithm steps described in the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians 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.

[0120] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0121] In several embodiments provided by the present application, if any function 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, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (hereinafter referred to as ROM), random access memories (hereinafter referred to as RAM), magnetic disks, or optical discs that can store program codes.

[0122] The above are only embodiments of the present invention, and thus do not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall similarly be included within the patent protection scope of the present invention.

Claims

1. A method for identifying the state of an electronic voltage transformer under finite samples, characterized in that: The following steps are involved: Collect the operation data of the electronic voltage transformer and pre-process the operation data; Create an initial feature set based on the preprocessed running data, set a feature combination strategy to recombine the initial feature set, and obtain a fused feature set; Constructing an operation data sample expansion model, training the operation data sample expansion model based on the fusion feature set, expanding the operation data through the trained operation data sample expansion model, and obtaining an operation data expansion sample set; Based on the DBSCAN algorithm, an electronic voltage transformer state recognition model is constructed, and the parameters of the electronic voltage transformer state recognition model are adaptively adjusted based on the line topology characteristics of the electronic voltage transformer. The specific steps are as follows: Based on the electronic voltage transformer topology information, a line topology characteristic graph of the electronic voltage transformer is constructed, wherein each node of the graph represents an electronic voltage transformer, and each edge of the graph represents a connection status between the electronic voltage transformers; For each node in the voltage transformer topology characteristic graph, its local density index is calculated, as shown in the following formula: ； in: Indicates The local density index of each node; Indicates A node and its Distances of neighboring points; Calculate the topological weight of each node as shown below: ； in: Indicates The topological weight of each node; Indicates The number of connections between a node and other nodes; Indicates the total number of nodes; , Represent the importance coefficients of the current node degree and the total number of nodes respectively; Initialize the initial radius and initial minimum number of sample points of the DBSCAN algorithm; For each node, the minimum number of sample points is adjusted according to its topological weight, as shown in the following formula: ； in: Indicates The minimum number of sample points after node adjustment; Indicates the initial minimum number of sample points; For each node, its radius is adjusted based on the local density index, as shown in the following formula: ； in: Indicates The radius of each node after adjustment; represents the initial radius; Represents the average value of local density index; represents the adjustment factor; For each node that the DBSCAN algorithm has not visited, determine whether it is a core point. If it is a core point, start a new cluster and recursively expand the cluster; Mark non-core points as boundary points, mark isolated points that cannot be expanded as noise points, and treat noise points as outliers; The adaptive adjustment parameters are applied to the electronic voltage transformer state recognition model, and the electronic voltage transformer state is identified by expanding the sample set through running data.

2. The method for identifying the state of an electronic voltage transformer under limited samples according to claim 1 is characterized in that: The operation data of the electronic voltage transformer includes voltage waveform, current waveform, temperature and humidity; The running data is normalized as shown in the following formula: ； in: Indicates the collected operation data; represents the mean of the running data; represents the standard deviation of the running data; Represents normalized running data.

3. The method for identifying the state of an electronic voltage transformer under finite samples according to claim 1, characterized in that: An initial feature set is created based on the preprocessed operating data, wherein the initial feature set includes a mean, a variance, a skewness, a kurtosis, a waveform factor, and a kurtosis index of the preprocessed operating data.

4. The method for identifying the state of an electronic voltage transformer under finite samples according to claim 1, characterized in that: The running data sample expansion model is constructed based on the GAN model.

5. The method for identifying the state of an electronic voltage transformer under limited samples according to claim 4 is characterized in that: Set the feature combination strategy to recombine the initial feature set to obtain the fused feature set, specifically: For each feature sample in the initial feature set, calculate its impact on the output of the running data sample expansion model, as shown in the following formula: ； in: Indicates running the data sample expansion model function; represents the initial feature set; represents the first Feature samples; Indicates The influence of each characteristic sample; The influence of all feature samples is normalized, and based on the normalized influence of the feature samples, the weight of each feature sample is calculated and nonlinear transformation is performed, as shown in the following formula: ； in: Indicates feature sample weights; After normalization, Feature samples; After normalization, Feature samples; represents a natural constant; Each feature sample is weighted and fused with its corresponding weight to obtain a fused feature set.

6. The method for identifying the state of an electronic voltage transformer under limited samples according to claim 5, characterized in that: The fused feature set is introduced into the GAN model discriminator as conditional information, as shown in the following formula: ； in: represents the discriminator function; represents the fusion feature set; Indicates true or false labels; Represents normalized running data; During the training process, the initial feature set is used as the conditional vector, and a random noise vector is created at the same time. The conditional vector and the random noise vector are input into the GAN model generator to generate samples. The discriminator is then used to determine the true or false labels of the generated samples. The loss is calculated based on the judgment accuracy, and the GAN model parameters are updated based on the loss through the back propagation algorithm.

7. An electronic voltage transformer state identification system under limited samples, used in the method according to any one of claims 1 to 6, characterized in that: It includes data acquisition module, feature fusion module, sample expansion module and state recognition module; The data acquisition module is used to collect the operation data of the electronic voltage transformer and pre-process the operation data; The feature fusion module is used to create an initial feature set based on the preprocessed running data, set a feature combination strategy to recombine the initial feature set, and obtain a fused feature set; The sample expansion module is used to construct an operation data sample expansion model, train the operation data sample expansion model based on the fusion feature set, expand the operation data through the trained operation data sample expansion model, and obtain an operation data expansion sample set; The state recognition module is used to construct an electronic voltage transformer state recognition model based on the DBSCAN algorithm, and adaptively adjust the parameters of the electronic voltage transformer state recognition model based on the line topology characteristics of the electronic voltage transformer; apply the adaptively adjusted parameters to the electronic voltage transformer state recognition model, and identify the electronic voltage transformer state by expanding the sample set through running data.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images