Voltage transformer error state evaluation method and system considering multi-dimensional attributes

Abstract

The invention belongs to the technical field of voltage transformer operation state monitoring, and particularly relates to a voltage transformer error state evaluation method and system considering multi-dimensional attributes, and the method comprises the steps: obtaining the state data of a voltage transformer in a transformer substation, the voltage transformer state data at least comprises historical secondary side output data and historical environment influence factor data; performing feature extraction on the obtained historical secondary side output data and historical environmental influence factor data to obtain multi-dimensional attribute features of the voltage transformer; carrying out adaptive weighted fusion on the obtained multi-dimensional attribute features and historical environment influence factor data to obtain multi-dimensional attribute fusion features; and predicting the operation error of the voltage transformer according to the obtained multi-dimensional attribute fusion features and the radial basis function neural network, and completing the voltage transformer error state evaluation considering the multi-dimensional attributes.

Description

Technical Field

[0001] The present invention belongs to the technical field of voltage transformer operating status monitoring, and in particular relates to a voltage transformer error status evaluation method and system considering multi-dimensional attributes. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] As an important part of the electric energy metering device, the accuracy and reliability of the transformer's metering performance is directly related to the fairness of electric energy trade settlement. Voltage transformer (CT) is a general-purpose device that converts high voltage into low voltage to achieve measurement; after voltage reduction and isolation, as an instrument for voltage conversion, it can also couple the carrier frequency to the transmission line for long-distance communication, selective line high-frequency protection, remote control and other functions.

[0004] During the long-term operation of voltage transformers, affected by the error collection principle and harsh environment, the measurement error of voltage transformers will deteriorate, and even serious measurement deviations will exceed the limit within the working life, which will lead to improper intervention and abnormal operation of the power grid automation system. Therefore, it is necessary to carry out error evaluation of voltage transformers, monitor the operating status of voltage transformers in real time, understand the measurement status of voltage transformers in real time, and promptly detect the degradation of the voltage transformer status to ensure the safe and stable operation of the power grid.

[0005] The existing voltage transformer error assessment can adopt an offline detection method, that is, to judge the working status of the voltage transformer in the power outage state. However, due to the small number of planned power outage windows and short time, offline detection is difficult to complete on schedule and cannot provide a theoretical basis for formulating maintenance plans. At the same time, offline detection cannot be combined with other voltage transformers in the area for data collection, resulting in a single type of collected data, and it is difficult to effectively utilize the transformer collection data of the topologically related opposite station, resulting in low evaluation accuracy.

[0006] Regarding the evaluation of the metering status of voltage transformers, relevant studies have constructed topological associations of multi-branch substations to collect voltage amplitude time series data of each branch; decompose the voltage amplitude time series data into trend quantity, seasonal quantity, periodic quantity and random quantity sequence data, and then perform feature extraction to obtain feature quantities; obtain the error value between the historical branch voltage amplitude data and the historical offline voltage amplitude data in the same area, and then calculate the correlation coefficient between the feature quantity and the error value as the feature contribution; generate feature data according to the feature contribution, input it into the density clustering network, adjust the parameters of the density clustering network, output an abnormal cluster, and use the cluster as a cluster of abnormal points to obtain the corresponding abnormal voltage transformer; however, in the evaluation process, only the trend quantity, seasonal quantity and periodic quantity of the time series data are considered, and the stationarity, drift and correlation of the time series data are not used as evaluation indicators, lacking a certain degree of mining of the deep properties of the time series data. Summary of the invention

[0007] To solve the above problems, the present invention proposes a voltage transformer error state evaluation method and system considering multi-dimensional attributes, extracts multi-dimensional attribute data of the secondary side data of the voltage transformer, performs deep mining on the data at the time series level, and adaptively weightedly fuses the obtained multi-dimensional attribute characteristics and environmental influencing factor data to obtain the operating error state of the voltage transformer. Combined with the obtained voltage transformer operating error state, the voltage transformer with poor state is discovered in time, the accuracy of the voltage transformer error state evaluation is improved, and the operation and maintenance efficiency of the voltage transformer is further improved.

[0008] According to some embodiments, a first solution of the present invention provides a voltage transformer error state evaluation method considering multi-dimensional attributes, using the following technical solution: A voltage transformer error state evaluation method considering multi-dimensional attributes, comprising: Acquiring status data of a voltage transformer in a substation, wherein the status data of the voltage transformer at least includes historical secondary side output data and historical environmental influencing factor data; Perform feature extraction on the acquired historical secondary side output data and historical environmental influencing factor data to obtain multi-dimensional attribute features of the voltage transformer; The obtained multi-dimensional attribute features and historical environmental influencing factor data are adaptively weighted fused to obtain multi-dimensional attribute fusion features; The operating error of the voltage transformer is predicted based on the obtained multi-dimensional attribute fusion features and radial basis function neural network, and the error state evaluation of the voltage transformer considering the multi-dimensional attributes is completed.

[0009] As a further technical limitation, the seasonal trend decomposition method based on Loess is used to decompose the time series characteristics of the obtained historical secondary output data, and the obtained ; Wherein, X represents the historical secondary side output data, S represents the seasonal term in the historical secondary side output data, T represents the trend term in the historical secondary side output data, and R represents the remainder term in the historical secondary side output data; the obtained multidimensional attribute characteristics of the voltage transformer include at least trend characteristics, seasonal characteristics, stability characteristics, drift characteristics and correlation characteristics.

[0010] As a further technical limitation, in the process of adaptively weighted fusion of the obtained multidimensional attribute features and historical environmental influencing factor data, feature extraction is performed on the historical environmental influencing factor data and the multidimensional attribute features respectively, and the extracted features are average pooled to reduce the dimension, and then the features after the average pooling operation are feature spliced, and the spliced ​​features are input into the fully connected layer. The output of the fully connected layer is normalized in combination with the Softmax function to obtain the multidimensional attribute feature weight coefficient matrix and the historical environmental influencing factor data weight coefficient matrix respectively.

[0011] Furthermore, the multidimensional attribute features and the historical environmental influencing factor data are weighted and summed according to the obtained multidimensional attribute feature weight coefficient matrix and the historical environmental influencing factor data weight coefficient matrix to obtain the multidimensional attribute fusion feature of the voltage transformer.

[0012] As a further technical limitation, the acquired status data of the voltage transformer in the substation also includes historical error status data; the operating error of the voltage transformer is predicted based on the obtained multi-dimensional attribute fusion characteristics and radial basis function neural network to obtain the predicted value of the voltage transformer error status data; by comparing the historical error status data with the predicted value of the voltage transformer error status data, the adopted radial basis function neural network is continuously adjusted to complete the training of the radial basis function neural network.

[0013] As a further technical limitation, the error state evaluation of the voltage transformer considering multi-dimensional attributes is completed by accuracy and precision; wherein, the accuracy is the probability that the error estimation state is consistent with the actual state, and the precision is the probability that all voltage transformers judged to be out of tolerance are actually out of tolerance.

[0014] According to some embodiments, a second solution of the present invention provides a voltage transformer error state evaluation system considering multi-dimensional attributes, which adopts the following technical solution: A voltage transformer error state evaluation system considering multi-dimensional attributes, comprising: An acquisition module, configured to acquire status data of a voltage transformer in a substation, wherein the status data of the voltage transformer at least includes historical secondary side output data and historical environmental influencing factor data; An extraction module is configured to perform feature extraction on the acquired historical secondary side output data and historical environmental influencing factor data to obtain multi-dimensional attribute features of the voltage transformer; A fusion module is configured to perform adaptive weighted fusion on the obtained multidimensional attribute features and historical environmental influencing factor data to obtain multidimensional attribute fusion features; The evaluation module is configured to predict the operating error of the voltage transformer based on the obtained multi-dimensional attribute fusion features and the radial basis function neural network, and complete the error state evaluation of the voltage transformer considering the multi-dimensional attributes.

[0015] According to some embodiments, a third solution of the present invention provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium stores a program thereon, which, when executed by a processor, implements the steps in a voltage transformer error state evaluation method considering multi-dimensional attributes as described in the first solution of the present invention.

[0016] According to some embodiments, a fourth solution of the present invention provides an electronic device, which adopts the following technical solution: An electronic device comprises a memory, a processor and a program stored in the memory and running on the processor, wherein when the processor executes the program, the steps in a method for evaluating a voltage transformer error state considering multi-dimensional attributes as described in the first solution of the present invention are implemented.

[0017] According to some embodiments, a fifth solution of the present invention provides a computer program product, which adopts the following technical solution: A computer program product comprises software codes, wherein the program in the software codes executes the steps in a voltage transformer error state evaluation method considering multi-dimensional attributes as described in the first solution of the present invention.

[0018] Compared with the prior art, the present invention has the following beneficial effects: The present invention extracts multidimensional attribute data of the secondary side data of the voltage transformer, performs deep mining on the data at the time series level, and adaptively weightedly fuses the obtained multidimensional attribute characteristics and environmental influencing factor data to obtain the operating error state of the voltage transformer. The voltage transformer with a poor state is discovered in time in combination with the obtained operating error state of the voltage transformer, thereby improving the accuracy of the error state evaluation of the voltage transformer and further improving the operation and maintenance efficiency of the voltage transformer. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings in the specification that constitute a part of this embodiment are used to provide a further understanding of this embodiment. The schematic embodiments of this embodiment and their descriptions are used to explain this embodiment and do not constitute improper limitations on this embodiment.

[0020] Figure 1 This is a flow chart of a voltage transformer error state evaluation method considering multi-dimensional attributes in Embodiment 1 of the present invention; Figure 2 This is a flow chart of radial basis function neural network training in embodiment 1 of the present invention; Figure 3 This is a structural block diagram of a voltage transformer error state evaluation system considering multi-dimensional attributes in Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0021] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0022] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0023] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0024] In the present invention, terms such as "upper", "lower", "left", "right", "front", "back", "vertical", "horizontal", "side", "bottom", etc. indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings. They are relational words determined only for the convenience of describing the structural relationships of the various parts or elements of the present invention, and do not specifically refer to any part or element in the present invention and should not be understood as limitations on the present invention.

[0025] In the present invention, terms such as "fixed connection", "connected", "connection", etc. should be understood in a broad sense, indicating that it can be fixedly connected, integrally connected or detachably connected; it can be directly connected or indirectly connected through an intermediate medium. For relevant scientific research or technical personnel in this field, the specific meanings of the above terms in the present invention can be determined according to specific circumstances, and they cannot be understood as limitations on the present invention.

[0026] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0027] Embodiment 1 Embodiment 1 of the present invention introduces a voltage transformer error state evaluation method considering multi-dimensional attributes.

[0028] like Figure 1 A voltage transformer error state evaluation method considering multi-dimensional attributes is shown, comprising the following steps: Step S100: Acquire historical secondary side output data X, historical environmental impact factor data E, and historical error state data Y of CT in the substation; Step S200: Extract features from the CT historical secondary output data X and historical environmental influencing factor data E to obtain multi-dimensional attribute features , where multidimensional attribute features Including trend features , seasonal characteristics , Stability Characteristics , drift characteristics , correlation characteristics ; Step S300: Use historical environmental influencing factor data E and multi-dimensional attribute features As input and historical error state data Y as output, the RBF model (Radial Basis Function Neural Network) based on the adaptive weighted fusion strategy is trained to obtain a trained CT operation error prediction model; Step S400: using the trained CT operation error prediction model to predict the CT operation error to be evaluated.

[0029] As one or more implementation methods, the obtained historical secondary side output data is decomposed into time series features using the seasonal trend decomposition method based on Loess, that is, (1); Among them, X represents the historical secondary side output data, S represents the seasonal term in the historical secondary side output data, T represents the trend term in the historical secondary side output data, and R represents the remainder term in the historical secondary side output data; the obtained multidimensional attribute characteristics of the voltage transformer at least include trend characteristics, seasonal characteristics, stability characteristics, drift characteristics and correlation characteristics.

[0030] Multi-dimensional attribute feature extraction is performed based on the decomposed historical secondary side output data, specifically: (1) Trend characteristics

[0031] The trend characteristics It is used to represent the long-term change pattern of the secondary side output data over time, namely: (2); in, Represents variance.

[0032] (2) Seasonal characteristics

[0033] The seasonal characteristics It is used to indicate that the secondary output data repeats at a specific interval over time, that is: (3); in, Represents variance.

[0034] (3) Stability characteristics

[0035] The stationarity feature The statistical characteristics of each order (such as mean and variance) used to represent the secondary side output data do not change with time, that is: Perform ADF (Augmented Dickey-Fuller test, unit root test) check on the historical secondary output data X. If it is stable, it is recorded as 1, and if it is not stable, it is recorded as 0, as follows: (4); (4) Drift characteristics

[0036] The drift characteristics It is used to represent the phenomenon that the probability distribution of the secondary side output data changes with time, that is: (5); (6); Where i represents the i-th first time window, m represents the total number of first time windows, represents the probability distribution decision value, f represents the implicit function, represents the minimum value of the secondary output data in the i-th first time window, represents the maximum value of the secondary output data in the i-th first time window, represents the variance of the secondary output data in the i-th first time window, Represents the mean of the secondary output data in the i-th first time window.

[0037] (5) Correlation characteristics

[0038] The correlation characteristics It is used to express the correlation between the secondary side output data and the environmental impact factor data E, that is: (7); Wherein, j represents the jth second time window, n represents the total number of second time windows, represents the secondary side voltage data of the jth second time window, represents the environmental influencing factor data of the j-th second time window, r represents the correlation implicit function, and P represents the correlation between the secondary side output data and the environmental influencing factor data of the j-th second time window; that is, (8); Among them, mean represents the mean and var represents the variance.

[0039] As one or more embodiments, Figure 2 The flowchart of radial basis function neural network training shown includes the following steps: Step S301: respectively analyze the historical environmental influencing factor data E and the multi-dimensional attribute features Perform feature extraction, perform average pooling on the two extracted features to reduce the dimension, perform feature splicing on the features after the average pooling operation, input the spliced ​​features into the fully connected layer, and normalize the output of the fully connected layer with the Softmax function to obtain the multi-dimensional attribute feature weight coefficient matrix and historical environmental impact factor data weight coefficient matrix ; Step S302: historical environmental influencing factor data E, multi-dimensional attribute features Respectively with the weight coefficient matrix of historical environmental influencing factors data and multi-dimensional attribute feature weight coefficient matrix Perform weighted summation to obtain the multi-dimensional attribute fusion characteristics of the voltage transformer; Step S303: input the obtained multi-dimensional attribute fusion features of the voltage transformer into the RBF network to obtain a trained CT operation error prediction model.

[0040] It should be noted that the RBF network used in this embodiment should belong to the existing technology that those skilled in the art should know, and this embodiment will not be described in detail here.

[0041] This embodiment evaluates the error state of the transformer and promptly finds the transformer with an abnormality, thereby ensuring the stability of the power grid operation.

[0042] In order to verify the effectiveness of the method proposed in this embodiment, numerical simulation is used to verify that 5 sets of qualified CT secondary output and environmental influencing factor data are collected in the substation to construct an online monitoring data set; by adding different human errors to the online monitoring data set, a large amount of error state data with known error states can be constructed.

[0043] Define the CT operating status out of tolerance as a positive example, and the CT operating status normal as a negative example. Count the number of correct and incorrect positive and negative examples respectively, and use the accuracy ACC and precision P as the effectiveness measurement indicators. The accuracy describes the probability that the error estimation state of this method is consistent with the actual state, and the precision describes the probability that the actual out-of-tolerance CT is actually out of tolerance among all the CTs judged to be out of tolerance. The calculation formulas are shown in formula (9) and formula (10), that is, (9); (10); Among them, TP means that the sample is positive and the prediction result is positive; FP means that the sample is negative and the prediction result is positive; TN means that the sample is negative and the prediction result is negative; FN means that the sample is positive and the prediction result is negative.

[0044] The identification accuracy and precision of each CT are shown in Table 1 and Table 2 respectively. The above experimental results show that the method of the present invention can accurately identify out-of-tolerance CTs and greatly improve the maintenance efficiency of faulty CTs.

[0045] Table 1 Single prediction results of the method in this embodiment

[0046] Table 2 Identification accuracy and precision of each CT

[0047] This embodiment extracts multidimensional attribute data of the secondary side data of the voltage transformer, conducts deep mining of the data at the time series level, and adaptively weighted fuses the obtained multidimensional attribute characteristics and environmental influencing factor data to obtain the operating error state of the voltage transformer. Combined with the obtained operating error state of the voltage transformer, the voltage transformer with poor status is discovered in time, the accuracy of the voltage transformer error state assessment is improved, and the operation and maintenance efficiency of the voltage transformer is further improved.

[0048] Embodiment 2 Embodiment 2 of the present invention introduces a voltage transformer error state evaluation system considering multi-dimensional attributes.

[0049] like Figure 3 A voltage transformer error state evaluation system considering multi-dimensional attributes is shown, comprising: An acquisition module, configured to acquire status data of a voltage transformer in a substation, wherein the status data of the voltage transformer at least includes historical secondary side output data and historical environmental influencing factor data; An extraction module is configured to perform feature extraction on the acquired historical secondary side output data and historical environmental influencing factor data to obtain multi-dimensional attribute features of the voltage transformer; A fusion module is configured to perform adaptive weighted fusion on the obtained multidimensional attribute features and historical environmental influencing factor data to obtain multidimensional attribute fusion features; The evaluation module is configured to predict the operating error of the voltage transformer based on the obtained multi-dimensional attribute fusion features and the radial basis function neural network, and complete the error state evaluation of the voltage transformer considering the multi-dimensional attributes.

[0050] The detailed steps are the same as those of the voltage transformer error state evaluation method considering multi-dimensional attributes provided in Example 1, and will not be repeated here.

[0051] Embodiment 3 Embodiment 3 of the present invention provides a computer-readable storage medium.

[0052] A computer-readable storage medium stores a program thereon, and when the program is executed by a processor, the program implements the steps in a voltage transformer error state evaluation method considering multi-dimensional attributes as described in Embodiment 1 of the present invention.

[0053] The detailed steps are the same as those of the voltage transformer error state evaluation method considering multi-dimensional attributes provided in Example 1, and will not be repeated here.

[0054] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The solutions in the embodiments of the present invention may be implemented in various computer languages, for example, object-oriented programming language Java and interpreted scripting language JavaScript, etc.

[0055] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0056] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0057] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0058] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0059] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

[0060] Embodiment 4 A fourth embodiment of the present invention provides an electronic device.

[0061] An electronic device comprises a memory, a processor and a program stored in the memory and running on the processor, wherein when the processor executes the program, the steps in a method for evaluating a voltage transformer error state considering multi-dimensional attributes as described in Embodiment 1 of the present invention are implemented.

[0062] The detailed steps are the same as those of the voltage transformer error state evaluation method considering multi-dimensional attributes provided in Example 1, and will not be repeated here.

[0063] Embodiment 5 Embodiment 5 of the present invention provides a computer program product.

[0064] A computer program product includes software codes, wherein the program in the software codes executes the steps in a voltage transformer error state evaluation method considering multi-dimensional attributes as described in Embodiment 1 of the present invention.

[0065] The detailed steps are the same as those of the voltage transformer error state evaluation method considering multi-dimensional attributes provided in Example 1, and will not be repeated here.

[0066] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The solutions in the embodiments of the present invention may be implemented in various computer languages, for example, object-oriented programming language Java and interpreted scripting language JavaScript, etc.

[0067] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0068] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0069] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0070] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0071] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

[0072] The above description is only a preferred embodiment of the present embodiment and is not intended to limit the present embodiment. For those skilled in the art, the present embodiment may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present embodiment shall be included in the protection scope of the present embodiment.

Claims

1. A voltage transformer error state evaluation method considering multi-dimensional attributes, characterized in that: include: Acquire status data of a voltage transformer in a substation, wherein the status data of the voltage transformer at least includes historical secondary side output data and historical environmental influencing factor data; Perform feature extraction on the acquired historical secondary side output data and historical environmental influencing factor data to obtain multi-dimensional attribute features of the voltage transformer; The obtained multi-dimensional attribute features and historical environmental influencing factor data are adaptively weighted fused to obtain multi-dimensional attribute fusion features; The operating error of the voltage transformer is predicted based on the obtained multi-dimensional attribute fusion features and radial basis function neural network, and the error state evaluation of the voltage transformer considering the multi-dimensional attributes is completed.

2. A voltage transformer error state evaluation method considering multi-dimensional attributes as described in claim 1, characterized in that: The seasonal trend decomposition method based on Loess is used to decompose the time series characteristics of the historical secondary output data, and the obtained ; Wherein, X represents the historical secondary side output data, S represents the seasonal term in the historical secondary side output data, T represents the trend term in the historical secondary side output data, and R represents the remainder term in the historical secondary side output data; the obtained multidimensional attribute characteristics of the voltage transformer include at least trend characteristics, seasonal characteristics, stability characteristics, drift characteristics and correlation characteristics.

3. A voltage transformer error state evaluation method considering multi-dimensional attributes as claimed in claim 1, characterized in that: In the process of adaptively weighted fusion of the obtained multidimensional attribute features and historical environmental influencing factor data, feature extraction is performed on the historical environmental influencing factor data and the multidimensional attribute features respectively, and the extracted features are average pooled to reduce the dimension. The features after the average pooling operation are then feature spliced, and the spliced ​​features are input into the fully connected layer. The output of the fully connected layer is normalized in combination with the Softmax function to obtain the multidimensional attribute feature weight coefficient matrix and the historical environmental influencing factor data weight coefficient matrix respectively.

4. A voltage transformer error state evaluation method considering multi-dimensional attributes as claimed in claim 3, characterized in that: According to the obtained multidimensional attribute feature weight coefficient matrix and the historical environmental influencing factor data weight coefficient matrix, the multidimensional attribute features and the historical environmental influencing factor data are weighted and summed to obtain the multidimensional attribute fusion features of the voltage transformer.

5. A voltage transformer error state evaluation method considering multi-dimensional attributes as claimed in claim 1, characterized in that: The acquired status data of the voltage transformer in the substation also includes historical error status data; the operating error of the voltage transformer is predicted based on the obtained multi-dimensional attribute fusion characteristics and the radial basis function neural network to obtain the predicted value of the voltage transformer error status data; by comparing the historical error status data with the predicted value of the voltage transformer error status data, the radial basis function neural network used is continuously adjusted to complete the training of the radial basis function neural network.

6. A voltage transformer error state evaluation method considering multi-dimensional attributes as claimed in claim 1, characterized in that: The error state evaluation of the voltage transformer considering multi-dimensional attributes is completed through accuracy and precision; wherein, the accuracy is the probability that the error estimation state is consistent with the actual state, and the precision is the probability that all voltage transformers judged to be out of tolerance are actually out of tolerance.

7. A voltage transformer error state evaluation system considering multi-dimensional attributes, characterized in that: include: An acquisition module, configured to acquire status data of a voltage transformer in a substation, wherein the status data of the voltage transformer at least includes historical secondary side output data and historical environmental influencing factor data; An extraction module is configured to perform feature extraction on the acquired historical secondary side output data and historical environmental influencing factor data to obtain multi-dimensional attribute features of the voltage transformer; A fusion module is configured to perform adaptive weighted fusion on the obtained multidimensional attribute features and historical environmental influencing factor data to obtain multidimensional attribute fusion features; The evaluation module is configured to predict the operating error of the voltage transformer based on the obtained multi-dimensional attribute fusion features and the radial basis function neural network, and complete the error state evaluation of the voltage transformer considering the multi-dimensional attributes.

8. A voltage transformer error state evaluation system considering multi-dimensional attributes as claimed in claim 7, characterized in that: In the fusion module, in the process of adaptively weighted fusion of the obtained multidimensional attribute features and historical environmental influencing factor data, feature extraction is performed on the historical environmental influencing factor data and the multidimensional attribute features respectively, and the extracted features are average pooled to reduce the dimension, and then the features after the average pooling operation are feature spliced, and the spliced ​​features are input into the fully connected layer. The output of the fully connected layer is normalized in combination with the Softmax function to obtain the multidimensional attribute feature weight coefficient matrix and the historical environmental influencing factor data weight coefficient matrix respectively.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of a method for evaluating a voltage transformer error state considering multi-dimensional attributes as described in any one of claims 1 to 6 are implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the steps of a method for evaluating a voltage transformer error state considering multi-dimensional attributes are implemented as described in any one of claims 1-6.

Images