Operation error prediction method and system of current transformer, medium and equipment

Abstract

The invention belongs to the technical field of current transformer operation, and particularly relates to an operation error prediction method and system of a current transformer, a medium and equipment, and the method comprises the steps: obtaining the error data and load data of the current transformer; performing correlation analysis on the obtained error data and load data to obtain a correlation coefficient between the current transformer error and the load; carrying out parameter correction on the long short-term memory network through residual bias estimation, and respectively predicting error data and load data of the current transformer according to the corrected long short-term memory network to obtain an error prediction value and a load prediction value; fusing the error prediction value and the load prediction value by using the correlation coefficient between the current transformer error and the load to obtain the prediction value of the operation error of the current transformer, and completing the operation error prediction of the current transformer; the prediction speed and precision are improved through parameter correction.

Description

Technical Field

[0001] The present invention belongs to the technical field of current transformer operation, and in particular relates to a method, system, medium and equipment for predicting operation errors of a current transformer. 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] Current is the core state variable of the power system and plays a key role in monitoring and maintaining the healthy operation of the power grid. The current transformer is an important measuring device in the power system. Its primary winding is connected in series in the main circuit of power transmission and transformation, and the secondary winding is connected to measuring instruments, relay protection or automatic devices according to different requirements. It is used to change the large current of the primary circuit into a small current on the secondary side for safe collection by measurement, control, protection and metering equipment. Therefore, the accurate and reliable operation of the current transformer is of great significance to the safe operation, control and protection, electric energy metering and trade settlement of the power system.

[0004] At present, the prediction and evaluation of the operation error of the current transformer usually adopts the method of offline verification or online verification, and the ratio error and angle error of the electronic current transformer are obtained by direct comparison. However, the evaluation and verification cycle is long, the on-site wiring is complicated, and the work efficiency is low. Some relevant scholars have proposed an error prediction strategy based on the Q-autoregressive moving average model (Q-ARMA) to improve the prediction accuracy of the electronic current transformer measurement data; however, it has certain limitations due to ignoring the ability of the time series model to capture long-term trends and periodic changes; at the same time, external factors are not comprehensively considered, especially the potential impact of line load changes on transformer measurement errors. Summary of the invention

[0005] In order to solve the above problems, the present invention proposes a method, system, medium and equipment for predicting the operation error of a current transformer. The model parameters are corrected by adding residual bias estimation to shorten the model training iterative calculation. At the same time, the load influence on the current transformer error is used to calibrate the current transformer error prediction value, thereby further improving the prediction accuracy.

[0006] According to some embodiments, a first solution of the present invention provides a method for predicting an operation error of a current transformer, using the following technical solution: A method for predicting an operation error of a current transformer, comprising: Obtain error data and load data of current transformer; Performing correlation analysis on the acquired error data and load data to obtain the correlation coefficient between the current transformer error and the load; The parameters of the long short-term memory network are corrected by residual bias estimation, and the error data and load data of the current transformer are predicted respectively according to the corrected long short-term memory network to obtain the error prediction value and the load prediction value; The correlation coefficient between the current transformer error and the load is used to fuse the error prediction value and the load prediction value, so as to obtain the prediction value of the current transformer operation error and complete the operation error prediction of the current transformer.

[0007] As a further technical limitation, the obtained error data and load data are normalized in magnitude so that the error data and load data can be fused and calculated, that is, ; ; in, and Respectively represent the data of a collection point in the transformer error and load data set, and They represent the data sets for collecting transformer error and load data respectively, and They respectively represent the current transformer error data and load data after magnitude normalization.

[0008] Furthermore, the correlation coefficient between the current transformer error and the load is obtained for ; in, Indicates the number of error data and load data of the current transformer obtained.

[0009] Furthermore, the predicted value of the current transformer operating error is obtained for ; in, and They represent the error prediction value and load prediction value of the current transformer respectively.

[0010] As a further technical limitation, a residual comparison module is added to the long short-term memory network to realize parameter correction of the long short-term memory network, and feedback adjustment of the long short-term memory network is realized by calculating the correction parameters of the long short-term memory network.

[0011] Furthermore, the parameter correction process of the long short-term memory network is: ; ; ; ; ; ; ; Where G is the correction factor, is the activation value of the forget gate, σ is the activation function; is the weight vector of the forget gate; “.” indicates the convolution operation; Represents the output of the memory unit at time t-1; represents the input at time t; Represents the bias term of the forget gate; Represents the activation value of the input; Represents the weight vector of the inputs; represents the bias term of the input gate; Indicates the temporary state of a memory cell; represents the weight vector of the output gate, Represents the bias term of the output gate.

[0012] According to some embodiments, a second solution of the present invention provides an operation error prediction system of a current transformer, which adopts the following technical solution: A system for predicting an operation error of a current transformer, comprising: An acquisition module, configured to acquire error data and load data of the current transformer; An analysis module is configured to perform a correlation analysis on the acquired error data and load data to obtain a correlation coefficient between the current transformer error and the load; A correction module is configured to correct the parameters of the long short-term memory network by estimating the residual bias, and predict the error data and the load data of the current transformer according to the corrected long short-term memory network to obtain an error prediction value and a load prediction value; The prediction module is configured to use the correlation coefficient between the current transformer error and the load to fuse the error prediction value and the load prediction value, obtain the prediction value of the current transformer operation error, and complete the operation error prediction of the current transformer.

[0013] 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, and when the program is executed by a processor, the program implements the steps in a method for predicting an operating error of a current transformer as described in the first embodiment of the present invention.

[0014] 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 predicting an operating error of a current transformer as described in the first embodiment of the present invention are implemented.

[0015] 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 the method for predicting an operation error of a current transformer as described in the first embodiment of the present invention.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The present invention sets a correction coefficient according to the residual between the long short-term memory network (LSTM) predicted value and the actual value, adaptively corrects the LSTM model parameters, shortens the model training iterative calculation, and improves the iteration speed of the model; extracts the trend of load and transformer error data by sliding average, and then analyzes the slope correlation of each point of the processed data to calibrate the current transformer predicted value, thereby improving the prediction accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] 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.

[0018] Figure 1 is a flow chart of a method for predicting an operating error of a current transformer in Embodiment 1 of the present invention; Figure 2 Schematic diagram of the structure of the operation error prediction model in the first embodiment of the present invention; Figure 3 This is a structural diagram of a method for predicting an operation error of a current transformer in Embodiment 1 of the present invention; Figure 4 Schematic diagram of evaluation index results of different detection methods in Example 1 of the present invention; Figure 5 This is a structural block diagram of an operation error prediction system for a current transformer in Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0019] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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.

[0024] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0025] Embodiment 1 Embodiment 1 of the present invention introduces a method for predicting an operation error of a current transformer.

[0026] In order to solve the problem that the traditional long short-term memory network cannot provide output feedback, resulting in low prediction accuracy, this embodiment adopts an improved long short-term memory network to predict the operating error of the current transformer. The parameters of the long short-term memory network are corrected by adding correction coefficients between the predicted value and the actual value, thereby speeding up the iterative calculation in the training stage. At the same time, the influence of the load on the current transformer error is used to calibrate the predicted value of the current transformer error, thereby improving the prediction accuracy.

[0027] like Figure 1 A method for predicting an operation error of a current transformer is shown, comprising the following steps: Step S100: collecting current transformer error data and line load data; Step S200: constructing an improved LSTM model; Step S300: training the prediction model by collecting data; Step S400: Fusion the prediction results of the two data to obtain current transformer error prediction data.

[0028] As one or more implementation modes, in step S100, the error data x of the transformer collected and the load data p of the corresponding line at the same time are not at the same order of magnitude, so the data need to be processed so that the two types of data can be fused and calculated.

[0029] Normalize the data, that is: ; ; Among them, x and p represent a data point in the transformer error and load data set, respectively. X and P They respectively represent the data sets for collecting transformer error and load data.

[0030] As one or more implementations, in step S200, although the convolutional neural network (CNN) is good at automatically discovering multi-level spatial features from data, it is not as effective as expected when processing time series data, especially those information that are highly dependent on time order. On the contrary, the long short-term memory network (LSTM) can effectively deal with the long-term dependency problem in the data through its unique gating mechanism design, showing its superiority in processing time series tasks. Error and load data are typical time series and have certain characteristics in the time dimension. However, due to the lack of a corresponding correction mechanism, it is impossible to adjust the process parameters according to the prediction results.

[0031] like Figure 2 As shown, this embodiment adds a residual comparison module to calculate the correction coefficient G of the model, realizes feedback adjustment of the LSTM prediction model, and enhances the prediction accuracy of the model. The specific calculation formula is: ; ; ; ; ; ; ; Where G is the correction factor, is the activation value of the forget gate, σ is the activation function; is the weight vector of the forget gate; “.” indicates the convolution operation; Represents the output of the memory unit at time t-1; represents the input at time t; Represents the bias term of the forget gate; Represents the activation value of the input; Represents the weight vector of the inputs; represents the bias term of the input gate; Indicates the temporary state of a memory cell; represents the weight vector of the output gate, Represents the bias term of the output gate.

[0032] As one or more implementation modes, the transformer error data and the load data are predicted respectively by improving LSTM, and then the prediction results of the two are merged by using the load influence value on the error to obtain the final transformer error prediction value.

[0033] Since the magnitude of the transformer error is greatly affected by the line load, when the load is large, the error will increase proportionally due to the increase in current. Therefore, to accurately predict the magnitude of the transformer error, it is necessary to consider the error value under different loads, obtain the best correlation coefficient through training data, obtain the influence of the load on the error, integrate the predicted transformer error and influence, and realize the calibration of the predicted value. Figure 3 shown.

[0034] This embodiment predicts the mutual inductor error and the load at the corresponding time respectively, and obtains the predicted values ​​of the two , and then process the predicted value according to the influence of load on the error, process the data by sliding average, and then calculate the slopes of the processed data segments, and judge the correlation according to the slope relationship between the two. Specifically: ; ; ; ; Among them, a represents the sliding window size, They represent the predicted value of transformer error and load respectively, β represents the influence of load on transformer error, d() represents derivative calculation, Ht represents the fused predicted value of transformer error, Indicates the number of error data and load data of the voltage transformer obtained.

[0035] The method in this embodiment is used to predict the current transformer error, and the RMSE and MAE commonly used in the regression algorithm are selected as comparative evaluation indicators. The obtained detection results are as follows: Figure 4 And as shown in Table 1.

[0036] Table 1 Comparison of different verification methods

[0037] This embodiment sets a correction coefficient according to the residual between the long short-term memory network (LSTM) predicted value and the actual value, corrects the model parameters by adding residual bias estimation, adaptively corrects the LSTM model parameters, shortens the model training iterative calculation, and improves the iteration speed of the model; extracts the trend of the load and transformer error data by sliding average, and then analyzes the slope correlation of each point of the processed data to calibrate the current transformer predicted value to improve the prediction accuracy.

[0038] Embodiment 2 Embodiment 2 of the present invention introduces an operation error prediction system for a current transformer.

[0039] like Figure 5 The operating error prediction system of a current transformer shown in the figure comprises: An acquisition module, configured to acquire error data and load data of the current transformer; An analysis module is configured to perform a correlation analysis on the acquired error data and load data to obtain a correlation coefficient between the current transformer error and the load; A correction module is configured to correct the parameters of the long short-term memory network by estimating the residual bias, and predict the error data and the load data of the current transformer according to the corrected long short-term memory network to obtain an error prediction value and a load prediction value; The prediction module is configured to use the correlation coefficient between the current transformer error and the load to fuse the error prediction value and the load prediction value, obtain the prediction value of the current transformer operation error, and complete the operation error prediction of the current transformer.

[0040] The detailed steps are the same as those of the method for predicting the operating error of a current transformer provided in Example 1, and will not be repeated here.

[0041] Embodiment 3 Embodiment 3 of the present invention provides a computer-readable storage medium.

[0042] 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 method for predicting an operating error of a current transformer as described in Embodiment 1 of the present invention.

[0043] The detailed steps are the same as those of the method for predicting the operating error of a current transformer provided in Example 1, and will not be repeated here.

[0044] 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.

[0045] 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.

[0046] 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 including 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.

[0047] 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.

[0048] 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.

[0049] 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.

[0050] Embodiment 4 A fourth embodiment of the present invention provides an electronic device.

[0051] 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 predicting an operating error of a current transformer as described in Embodiment 1 of the present invention are implemented.

[0052] The detailed steps are the same as those of the method for predicting the operating error of a current transformer provided in Example 1, and will not be repeated here.

[0053] Embodiment 5 Embodiment 5 of the present invention provides a computer program product.

[0054] A computer program product includes software codes, wherein the program in the software codes executes the steps in a method for predicting an operation error of a current transformer as described in Embodiment 1 of the present invention.

[0055] The detailed steps are the same as those of the method for predicting the operating error of a current transformer provided in Example 1, and will not be repeated here.

[0056] 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 method for predicting an operating error of a current transformer, characterized in that: include: Obtain error data and load data of current transformer; Performing correlation analysis on the acquired error data and load data to obtain the correlation coefficient between the current transformer error and the load; The parameters of the long short-term memory network are corrected by residual bias estimation, and the error data and load data of the current transformer are predicted respectively according to the corrected long short-term memory network to obtain the error prediction value and the load prediction value; The correlation coefficient between the current transformer error and the load is used to fuse the error prediction value and the load prediction value, so as to obtain the prediction value of the current transformer operation error and complete the operation error prediction of the current transformer.

2. A method for predicting an operation error of a current transformer as claimed in claim 1, characterized in that: The obtained error data and load data are normalized in magnitude so that the error data and load data can be fused and calculated, that is, ； ； in, and Respectively represent the data of a collection point in the transformer error and load data set, and They represent the data sets for collecting transformer error and load data respectively, and They respectively represent the current transformer error data and load data after magnitude normalization.

3. A method for predicting an operation error of a current transformer as claimed in claim 2, characterized in that: The obtained correlation coefficient between the current transformer error and the load for ； in, Indicates the number of error data and load data of the current transformer obtained.

4. A method for predicting an operation error of a current transformer as claimed in claim 3, characterized in that: The predicted value of the current transformer operating error obtained for ； in, and They represent the error prediction value and load prediction value of the current transformer respectively.

5. A method for predicting an operation error of a current transformer as claimed in claim 1, characterized in that: A residual comparison module is added to the long short-term memory network to realize parameter correction of the long short-term memory network, and feedback adjustment of the long short-term memory network is realized by calculating the correction parameters of the long short-term memory network.

6. A method for predicting an operation error of a current transformer as claimed in claim 5, characterized in that: The parameter correction process of the long short-term memory network is: ； ； ； ； ； ； ； Where G is the correction factor, is the activation value of the forget gate, σ is the activation function; is the weight vector of the forget gate; ". " represents the convolution operation; Represents the output of the memory unit at time t-1; represents the input at time t; Represents the bias term of the forget gate; Represents the activation value of the input; Represents the weight vector of the inputs; represents the bias term of the input gate; Indicates the temporary state of a memory cell; represents the weight vector of the output gate, Represents the bias term of the output gate.

7. A current transformer operation error prediction system, characterized in that: include: An acquisition module, configured to acquire error data and load data of the current transformer; An analysis module is configured to perform a correlation analysis on the acquired error data and load data to obtain a correlation coefficient between the current transformer error and the load; A correction module is configured to correct the parameters of the long short-term memory network by estimating the residual bias, and predict the error data and the load data of the current transformer according to the corrected long short-term memory network to obtain an error prediction value and a load prediction value; The prediction module is configured to use the correlation coefficient between the current transformer error and the load to fuse the error prediction value and the load prediction value, obtain the prediction value of the current transformer operation error, and complete the operation error prediction of the current transformer.

8. 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 predicting an operating error of a current transformer as described in any one of claims 1 to 6 are implemented.

9. 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 predicting an operating error of a current transformer as described in any one of claims 1-6 are implemented.

10. A computer program product comprising software code, characterized in that The program in the software code executes the steps of a method for predicting an operating error of a current transformer as described in any one of claims 1-6.

Images