A low-voltage current transformer live detection identification method based on similarity search and a storage medium

Abstract

This invention discloses a method and storage medium for live detection and identification of low-voltage current transformers based on similarity search. The method includes: Step S1: Receiving the output signal from the low-voltage current transformer, extracting features, and performing data conversion; Step S2: Comparing the converted digital signal with a pre-established transformer parameter database and performing a similarity search; Step S3: Determining the most matching transformer parameters based on the similarity search results and performing online identification; Step S4: Monitoring the transformer performance in real time and providing real-time feedback and adjustments based on the identification results. The storage medium stores a computer program used to execute the above method. This invention has advantages such as simple principle, good real-time performance, wide applicability, and high reliability.

Description

Technical Field

[0001] This invention mainly relates to the field of current transformer detection, specifically a method and storage medium for detecting and identifying live low-voltage current transformers based on similarity search. Background Technology

[0002] Current transformers are common and widely used electrical devices that convert high-current primary system circuits into low-current secondary system circuits to facilitate the use of measurement and protection devices.

[0003] Currently, with the development of the power grid industry, especially the separation of power generation and transmission implemented through power sector reforms, the accuracy, fairness, and impartiality of electricity metering have increasingly attracted attention. However, low-voltage electricity metering devices with load currents greater than 60A typically consist of an electricity meter and a low-voltage current transformer. Due to their wide application and large number, subsequent or in-use verification of low-voltage current transformers requires power outages and disconnection from the line. Therefore, aside from pre-installation verification, subsequent and in-use verifications are often not strictly conducted according to relevant regulations. If errors or inaccuracies occur during use and cannot be detected promptly, the entire electricity metering device will become inaccurate, seriously affecting the fairness and impartiality of metering.

[0004] As mentioned above, in practical applications, it is necessary to monitor the operating status and performance of the current transformer in real time. Under normal operating conditions, the various parameters of the current transformer can be continuously collected and analyzed in order to detect abnormalities in a timely manner and ensure the stable operation of the power system.

[0005] According to the relevant verification procedures for instrument transformers, the verification of the entire power grid metering system is currently carried out component by component. Low-voltage current transformers play a crucial role in industrial production, but their parameters gradually deviate from standard values ​​over time and under varying usage conditions, requiring periodic identification and calibration. Traditional identification methods typically involve offline testing and manual analysis, which is time-consuming and labor-intensive. Summary of the Invention

[0006] The technical problem to be solved by this invention is: in view of the technical problems existing in the prior art, this invention provides a low-voltage current transformer live detection and identification method and storage medium based on similarity search, which is simple in principle, has good real-time performance, wide applicability and high reliability.

[0007] To solve the above-mentioned technical problems, the present invention adopts the following technical solution:

[0008] A method for detecting and identifying live current transformers based on similarity search, comprising:

[0009] Step S1: Receive the output signal from the low-voltage current transformer, extract its features, and perform data conversion;

[0010] Step S2: Compare the converted digital signal with the pre-established transformer parameter database and perform a similarity search;

[0011] Step S3: Based on the similarity search results, determine the parameters of the most matching mutual inductor and perform online identification;

[0012] Step S4: Monitor the performance of the current transformer in real time, and provide real-time feedback and adjustments based on the identification results.

[0013] As a further improvement of the present invention: the similarity search process in step S3 includes:

[0014] Step S301: Extract features from the current transformer output signal;

[0015] Step S302: Compare the extracted features with each entry in the database and calculate the similarity between them;

[0016] Step S303: Based on the similarity measurement results, sort the entries in the database, set a threshold according to the application requirements, filter out the entries with a certain similarity, and select the top few entries with the highest similarity as candidates.

[0017] Step S304: Feed back the similarity search results to the system to determine the most matching transformer parameters.

[0018] As a further improvement of the present invention: in step S301, the feature is one or more of frequency domain features, time domain features, and phase features.

[0019] As a further improvement of the present invention: in step S303, the similarity measurement method is one or more of Euclidean distance, cosine similarity, and correlation coefficient.

[0020] As a further improvement of the present invention: the process of step S303 includes:

[0021] Step S3031: Set a similarity threshold to filter out database entries with similarity higher than the threshold;

[0022] Step S3032: For the selected candidates, compare the characteristics of the output signals of the other current transformers to ensure that the selected candidates have a high degree of matching.

[0023] As a further improvement of the present invention: the online identification process in step S3 includes:

[0024] Based on the results of the similarity search, the database entry with the highest similarity is selected as the current parameter estimate;

[0025] The extracted digital signals are compared with the database entries with the highest similarity, and the similarity between them is calculated.

[0026] Based on the similarity measurement results, the entries in the database are sorted, and the parameter with the best similarity is selected as the identification result.

[0027] The identified parameters or status are fed back to the system, continuously monitoring the system's status and parameters, updating and adjusting them based on real-time data, and using them for real-time monitoring and adjustment.

[0028] As a further improvement of the present invention: the data transformation adopts the zero-mean method, and the formula is as follows:

[0029]

[0030] For the original sequence C, it is standardized to sequence C', where u and v are the mean and standard deviation of the sequence, respectively.

[0031] As a further improvement of the present invention: the similarity measurement method is Euclidean distance, then the formula for calculating the Euclidean distance between the output signal sequence X = {X1, X2, ..., Xn} received from the low-voltage current transformer and the standard sequence Y = {Y1, Y2, ..., Yn} in the transformer parameter database is as follows:

[0032]

[0033] As a further improvement of the present invention: the process of establishing the pre-built transformer parameter database in step S2 includes:

[0034] Collect data on standard low-voltage current transformers under different operating conditions;

[0035] The collected data needs to be processed and analyzed in order to extract the characteristic parameters of the current transformer;

[0036] Based on the characteristic parameters obtained from processing and analysis, a mathematical model of the transformer parameters is established.

[0037] Based on the established mathematical model, the structure and format of the mutual inductor parameter database are set;

[0038] The collected data is labeled and verified by comparing it with known parameters.

[0039] The present invention further provides a storage medium that can be read by a computer or processor, wherein the storage medium stores a computer program for performing any of the above methods.

[0040] Compared with the prior art, the advantages of the present invention are as follows:

[0041] 1. The low-voltage current transformer live-line detection and identification method and storage medium based on similarity search of the present invention are simple in principle, have good real-time performance, wide applicability, and high reliability. By adjusting system parameters in real time according to the identification results, system performance can be optimized. For example, adjusting the system's control parameters based on changes in the transformer output signal improves the system's response speed, stability, and accuracy, thereby achieving better control effects.

[0042] 2. The low-voltage current transformer live-line detection and identification method and storage medium based on similarity search of the present invention provide real-time feedback and adjustment, and can further help the system detect potential faults in a timely manner, and perform diagnosis and handling. By comparing the identification results with expected values, the present invention can identify anomalies and take corresponding measures to prevent the further expansion of faults, thereby improving the reliability and safety of the system.

[0043] 3. The low-voltage current transformer live-line detection and identification method and storage medium based on similarity search of the present invention can provide real-time feedback and adjustment, and can further help the system optimize energy consumption. By adjusting the system's operating parameters according to real-time data, the present invention can reduce system energy consumption, improve energy utilization efficiency, thereby reducing operating costs and minimizing environmental impact.

[0044] 4. The low-voltage current transformer live-line detection and identification method and storage medium based on similarity search of the present invention can also achieve adaptive control by real-time feedback and adjustment based on the identification results. The system formed using the present invention can automatically adjust the control strategy and parameters according to the real-time monitored data to adapt to changes in the system's operating state, thereby achieving more flexible and efficient control.

[0045] 5. The low-voltage current transformer live-line detection and identification method and storage medium based on similarity search of the present invention can provide real-time feedback and adjustment as a continuous process. By continuously monitoring the system status and adjusting parameters, the system's performance and efficiency can be continuously optimized. The system can learn from historical data and feedback information and continuously improve the identification algorithm and control strategy, thereby achieving continuous performance improvement and optimization. Attached Figure Description

[0046] Figure 1 This is a flowchart illustrating the method of the present invention in a specific embodiment. Detailed Implementation

[0047] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0048] like Figure 1 As shown, this embodiment discloses a method for detecting and identifying live low-voltage current transformers based on similarity search, which includes:

[0049] Step S1: Receive the output signal from the low-voltage current transformer, extract its features, and perform data conversion;

[0050] Step S2: Compare the converted digital signal with the pre-established transformer parameter database and perform a similarity search;

[0051] Step S3: Based on the similarity search results, determine the parameters of the most matching mutual inductor and perform online identification;

[0052] Step S4: Monitor the performance of the current transformer in real time, and provide real-time feedback and adjustments based on the identification results.

[0053] In a specific application example, the pre-established transformer parameter database in step S2 specifically includes:

[0054] Collect data from standard low-voltage current transformers under different operating conditions; the data may include one or more parameters such as current value, phase angle, and frequency, depending on actual needs.

[0055] The collected data needs to be processed and analyzed in order to extract the characteristic parameters of the current transformer;

[0056] Based on the characteristic parameters obtained from processing and analysis, a mathematical model of the transformer parameters is established.

[0057] Based on the established mathematical model, the structure and format of the current transformer parameter database are set; the database can store and manage a large amount of parameter data and supports fast query and retrieval.

[0058] The collected data is labeled and verified by comparing it with known parameters.

[0059] In a specific application example, the process of performing a similarity search in step S3 includes:

[0060] Step S301: Extract features from the current transformer output signal;

[0061] The feature may be one or more of the following: frequency domain feature, time domain feature, phase feature, etc.

[0062] Step S302: Compare the extracted features with each entry in the database and calculate the similarity between them;

[0063] In practical applications, similarity measurement methods may include one or more of Euclidean distance, cosine similarity, correlation coefficient, etc.

[0064] Step S303: Based on the similarity measurement results, sort the entries in the database, set a threshold according to the application requirements, filter out the entries with a certain similarity, and select the top few entries with the highest similarity as candidates.

[0065] Step S304: Feed back the similarity search results to the system to determine the most matching transformer parameters.

[0066] Furthermore, in step S303, setting a threshold according to the application's needs, filtering out entries with similarity meeting certain requirements, and selecting the top few entries with the highest similarity as candidates specifically includes:

[0067] Step S3031: Set a similarity threshold to filter out database entries with a similarity higher than the threshold; the threshold can be determined according to the application requirements and system performance, and choosing a suitable similarity threshold can balance the accuracy and efficiency of the search.

[0068] Step S3032: For the selected candidates, further compare the characteristics of the output signals of the remaining current transformers to ensure that the selected candidates have a high degree of matching.

[0069] In a specific application example, step S3, the online identification process specifically includes:

[0070] Based on the results of the similarity search, the database entry with the highest similarity is selected as the current parameter estimate;

[0071] The extracted digital signals are compared with the database entries with the highest similarity, and the similarity between them is calculated.

[0072] Based on the similarity measurement results, the entries in the database are sorted, and the parameter with the best similarity is selected as the identification result.

[0073] The identified parameters or status are fed back to the system, continuously monitoring the system's status and parameters, updating and adjusting them based on real-time data, and using them for real-time monitoring and adjustment.

[0074] In a specific application example, the data transformation specifically employs the zero-mean method, and its formula is as follows:

[0075]

[0076] For the original sequence C, it is standardized to sequence C', where u and v are the mean and standard deviation of the sequence, respectively.

[0077] In a specific application example, the similarity measurement method is Euclidean distance. The formula for calculating the Euclidean distance between the output signal sequence X = {X1, X2, ..., Xn} received from the low-voltage current transformer and the standard sequence Y = {Y1, Y2, ..., Yn} in the transformer parameter database is as follows:

[0078]

[0079] The present invention further provides a storage medium that can be read by a computer or processor, wherein the storage medium stores a computer program for performing the above-described method.

[0080] Those skilled in the art will understand that the above embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create an implementation for the process. Figure 1 One or more processes and / or boxes Figure 1 The computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0081] The above are merely preferred embodiments of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principles of the present invention should be considered within the scope of protection of the present invention.

Claims

1. A method for detecting and identifying live current transformers based on similarity search, characterized in that, include: Step S1: Receive the output signal from the low-voltage current transformer, extract its features, and perform data conversion; Step S2: Compare the converted digital signal with the pre-established transformer parameter database and perform a similarity search; Step S3: Based on the similarity search results, determine the parameters of the mutual inductor with the best similarity match, as the identification result; Step S4: Adjust the system parameters in real time based on the identification results; The similarity search process in step S3 includes: Step S301: Extract features from the current transformer output signal; the features are one or more of frequency domain features, time domain features, and phase features; Step S302: Compare the extracted features with each entry in the database and calculate the similarity between them; Step S303: Based on the similarity measurement results, sort the entries in the database, set a threshold according to the application requirements, filter out entries with similarity that meet certain requirements, and select the top few entries with the highest similarity as candidates; set another similarity threshold to filter out database entries with similarity higher than the threshold; for the selected candidates, compare the characteristics of the output signals of the other current transformers to ensure that the selected candidates have a high degree of matching; the selected candidates are used as the results of the similarity search. Step S304: Feed back the similarity search results to the system to determine the parameters of the mutual inductor with the best similarity match.

2. The low-voltage current transformer live-line detection and identification method based on similarity search according to claim 1, characterized in that, In step S303, the similarity measurement method is one or more of Euclidean distance, cosine similarity, and correlation coefficient.

3. The low-voltage current transformer live-line detection and identification method based on similarity search according to claim 1, characterized in that, The data transformation uses the zero-mean method, and its formula is: For the original sequence Standardize it into a sequence , where u and v are the mean and standard deviation of the sequence, respectively; The similarity metric is Euclidean distance, then the received output signal sequence X = {X1, X2, ...} from the low-voltage current transformer is... The standard sequence Y={Y1, Y2, ..., Xn} and the mutual inductor parameter database are used to obtain the mutual inductor parameter database. The Euclidean distance between {Yn} is calculated as follows: 。 4. The method for live detection and identification of low-voltage current transformers based on similarity search according to any one of claims 1-3, characterized in that, In step S2, the process of establishing the pre-built transformer parameter database includes: Collect data on standard low-voltage current transformers under different operating conditions; The collected data needs to be processed and analyzed in order to extract the characteristic parameters of the current transformer; Based on the characteristic parameters obtained from processing and analysis, a mathematical model of the transformer parameters is established. Based on the established mathematical model, the structure and format of the mutual inductor parameter database are set; The collected data is labeled and verified by comparing it with known parameters.

5. A storage medium capable of being read by a computer or processor, characterized in that, The storage medium stores a computer program for performing any one of the methods of claims 1-4.

Images