A method for evaluating the metering error of voltage transformers

Abstract

This invention discloses a method for evaluating metering errors in voltage transformers, relating to the field of voltage transformer metering technology. It involves constructing a synchronous acquisition system for multiple voltage transformers within a substation to obtain raw voltage data, building a virtual reference voltage generation model, outputting a reference voltage sequence, calculating error statistical characteristics and labeling the operating status level of the voltage transformers, evaluating a health score based on the error characteristics, outputting the score result, receiving inspection feedback to compare differences and update the model, generating analysis charts and uploading them to a client for display and linkage with the operation and maintenance system. This invention provides a method for constructing a virtual reference voltage model to replace physical standards, enabling online error evaluation, fusing multi-source data, dynamically extracting error characteristics and labeling operating status, establishing a health score and early warning mechanism, and introducing a feedback closed loop to optimize model accuracy. The evaluation results are displayed in chart form, assisting operation and maintenance scheduling and improving the real-time performance, accuracy, and adaptability of the evaluation.

Description

Technical Field

[0001] This invention relates to the field of voltage transformer metering technology, and in particular to a method for evaluating voltage transformer metering errors. Background Technology

[0002] Voltage transformers, as crucial primary equipment for voltage monitoring and energy metering in power systems, directly impact the stability of power system operation and the fairness of user metering. Existing voltage transformer error assessment methods largely rely on offline laboratory calibration or periodic manual testing, which struggles to reflect dynamic error changes during operation in real time and cannot adapt to factors such as diverse substation structures, complex load conditions, and environmental fluctuations. Furthermore, some online assessment methods depend on physical standards or single-point reference data, resulting in assessment models lacking robustness and universality, exhibiting insufficient error coverage, weak dynamic adjustment capabilities, and a lack of self-learning ability.

[0003] Currently, Chinese patent application number CN201910892188.8 discloses a capacitive voltage transformer (CVT) metering error situation awareness system, comprising a data acquisition system, a data analysis system, and a situation prediction system connected in sequence. The data acquisition system collects real-time operating data of the CVT under test and its power system. Based on the data collected by the data acquisition system, the data analysis system analyzes the CVT metering error status. Based on the CVT metering error status analyzed by the data analysis system, the situation prediction system predicts the CVT metering error situation. This awareness system can promptly detect problems with CVT metering errors based on the CVT metering error situation and promptly repair the CVT, thereby avoiding economic losses caused by metering errors. Furthermore, this awareness system can also calculate the gradual process of CVT metering anomalies based on the current metering error status of the CVT, pinpoint the moment when a CVT malfunction occurs, and provide guidance for CVT repair and other related procedures.

[0004] The relevant technologies are insufficient to achieve online dynamic assessment and accurate classification of voltage transformer metering errors without the need for physical standards. Summary of the Invention

[0005] The technical problem solved by this invention is that related technologies are unable to achieve online dynamic evaluation and accurate classification of voltage transformer metering errors without the need for physical standards.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] A method for evaluating the metering error of a voltage transformer includes the following steps:

[0008] Step S1: Construct a synchronous acquisition system for multiple voltage transformers within the substation to obtain raw voltage data;

[0009] Step S2: Construct a virtual reference voltage generation model and output a reference voltage sequence;

[0010] Step S3: Calculate the error statistical characteristics and label the voltage transformer operating status level;

[0011] Step S4: Evaluate the health score based on the error characteristics and output the score result;

[0012] Step S5: Receive inspection feedback, compare differences, and update the model;

[0013] Step S6: Generate analysis charts and upload them to the client for display and linkage with the operation and maintenance system;

[0014] Step S2 includes the following sub-steps:

[0015] Step S201: Extract the physical voltage nodes corresponding to the voltage transformers in the substation and construct a logical connection diagram;

[0016] Step S202: Based on the logical relationship of the electrical nodes connected to the voltage transformer, analyze the voltage conduction path between the bus, incoming line and outgoing line, and construct a reference voltage function model;

[0017] The reference voltage function model includes the voltage relationship, transformer ratio, and coupling effects between each physical voltage node;

[0018] Step S203: Collect historical operating data, which includes the original voltage measurement data of the voltage transformers in multiple time periods, the corresponding substation operating condition information, and the actual load characteristics.

[0019] Based on the regular deviations, coordinated change trends, and static and dynamic relationships between node voltages in historical operating data, and combined with a preset rule set, which includes node voltage stability criteria, load regulation modes, and grid operating status classification rules, a virtual reference voltage generation model is constructed to fit the reference voltage. The virtual reference voltage generation model outputs an estimated value based on the comparison between the current node structure and historical patterns.

[0020] Step S204: Fit the current original voltage data using a virtual reference voltage generation model, and output a virtual reference voltage sequence that matches the actual nodes;

[0021] The reference voltage function model supports a dynamic parameter adaptive adjustment mechanism, which includes:

[0022] Determine the type of topology change based on real-time collected operational status data;

[0023] When a topology change event occurs, the node function parameters are recalculated and updated to the reference voltage function model;

[0024] Adjust parameters through incremental learning;

[0025] Preferably, the indicators of the coordinated change trend include:

[0026] Calculate the average rate of change of error within a sliding window to identify short-term fluctuation trends;

[0027] The rate of change of short-term fluctuations is extracted by second-order difference of the mean.

[0028] The drift slope is extracted as a long-term trend indicator by fitting the mean error trajectory using the least squares method.

[0029] Short-term fluctuation trends, short-term fluctuation rate of change, and long-term trend indicators are used as feature variables for state classification and scoring.

[0030] Preferably, step S1 includes the following sub-steps:

[0031] Step S101: Select multiple voltage transformers installed at specific busbar, incoming line and outgoing line locations in the substation as monitoring objects, covering the main voltage node areas, and record the installation point, operation number and electrical node information corresponding to each voltage transformer.

[0032] Step S102: Based on the high-precision optical fiber communication module, the voltage signal output from the secondary side of the voltage transformer is synchronously acquired with a unified time reference. The voltage signal comes from the transformation output of the bus, incoming or outgoing voltage measured by the voltage transformer in actual operation, forming structured raw voltage data.

[0033] Step S103: Upload the structured raw voltage data to the time series database to complete the format standardization conversion and field validation.

[0034] Preferably, step S3 includes the following sub-steps:

[0035] Step S301: Compare the original voltage measurement data with the virtual reference voltage sequence to generate a measurement error sequence;

[0036] Step S302: Perform sliding window segmentation statistics on the measurement error sequence, extract the mean, extreme range, variance and rate of change of the error, and output the voltage transformer error statistical feature data.

[0037] Step S303: Based on the classification criteria, a comprehensive analysis is performed on the statistical characteristic data of the voltage transformer error within each sliding time window. The logic of the comprehensive analysis is as follows:

[0038] The voltage transformer error statistical characteristic data is compared with the preset state classification standard. Based on the performance of the voltage transformer error statistical characteristic data on the preset state classification standard, the operating state level of the corresponding voltage transformer in the corresponding time window is marked and output. The operating state level includes normal, slightly abnormal, moderately abnormal and severely abnormal.

[0039] Preferably, step S4 includes the following sub-steps:

[0040] Step S401: Identify the periodic changes, continuous shifts, and sudden anomalies in the voltage transformer error statistical characteristic data, and construct an error characteristic mapping table;

[0041] Step S402: Refer to historical voltage error data and a preset scoring model. The scoring model is constructed based on the aforementioned voltage transformer error statistical characteristic data. Independent scoring factor weights are set for different characteristic dimensions. After normalization processing, the corresponding health factor score values ​​are calculated respectively.

[0042] Obtain health factor scores, perform weighted summation of health factor scores according to the weighted calculation rules set in the scoring model, and output a comprehensive health score result;

[0043] Step S403: When the comprehensive health score is lower than the preset warning threshold, the warning mechanism is triggered and a maintenance task signal is generated.

[0044] Preferably, the logic of step S403 is as follows:

[0045] Continuously compare the health scores and thresholds of the current transformers;

[0046] When the score is below the threshold, an inspection suggestion of the corresponding level is generated according to the scheduling rules;

[0047] Optimize the scheduling plan by combining the location of the current transformer, voltage level, and maintenance records;

[0048] Output maintenance scheduling suggestions and upload them to the operation and maintenance platform for the generation of work assignment instructions.

[0049] Preferably, step S5 includes the following sub-steps:

[0050] Step S501: Receive log feedback information, which includes inspection time, equipment number, inspection judgment label and on-site remarks.

[0051] The log feedback information is compared one by one with the voltage transformer error statistical feature data and the operating status level. The sample pairs that are consistent with the voltage transformer error statistical feature data and the sample pairs that are inconsistent are identified, the comparison results are output, and a difference comparison report is generated based on the comparison results. The difference comparison report includes the consistency ratio, the reason for the difference and the scope of the impact.

[0052] Step S502: Label the sample pairs that are determined to be consistent as reliable training samples and input them into the model training process of the error classification model and the virtual reference voltage generation model.

[0053] For sample pairs with inconsistent status labels, they are submitted to the expert system interface for manual verification and labeling, and high-confidence samples are output. These high-confidence samples are then input into the model training process of the error classification model and the virtual reference voltage generation model.

[0054] Preferably, step S6 includes the following sub-steps:

[0055] Step S601: Construct error line charts, scoring trend charts, and equipment level distribution charts from the measurement error sequence, comprehensive health score results, and operating status, respectively. The line charts, scoring trend charts, and equipment level distribution charts are then visualized and displayed after being converted to a unified format.

[0056] Step S602: Upload the line chart, rating trend chart, and equipment level distribution chart to the client platform.

[0057] The beneficial effects of this invention are as follows: This invention provides a method to construct a virtual reference voltage model to replace the physical standard, realize online error assessment, integrate multi-source data, dynamically extract error features and label the operating status, establish a health scoring and early warning mechanism, and introduce feedback closed loop to optimize model accuracy. The assessment results are displayed in the form of charts to assist operation and maintenance scheduling and improve the real-time performance, accuracy and adaptability of the assessment. Attached Figure Description

[0058] Figure 1 The flowchart illustrates the steps of a voltage transformer metering error assessment method according to an embodiment of the present invention. Detailed Implementation

[0059] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0060] Example, refer to Figure 1 A method for evaluating the metering error of a voltage transformer is provided, comprising the following steps:

[0061] Step S1: Construct a synchronous acquisition system for multiple voltage transformers within the substation to obtain raw voltage data.

[0062] Step S2: Construct a virtual reference voltage generation model and output a reference voltage sequence.

[0063] Step S3: Calculate the error statistical characteristics and label the voltage transformer operating status level.

[0064] Step S4: Evaluate the health score based on the error characteristics and output the score result.

[0065] Step S5: Receive inspection feedback, compare differences, and update the model.

[0066] Step S6: Generate analysis charts and upload them to the client for display and linkage with the operation and maintenance system.

[0067] Step S1 includes the following sub-steps:

[0068] Step S101: Select multiple voltage transformers installed at specific busbar, incoming line and outgoing line locations in the substation as monitoring objects, covering the main voltage node areas, and record the installation point, operation number and electrical node information corresponding to each voltage transformer.

[0069] Step S101 achieves monitoring coverage of key voltage nodes in the substation, ensuring the representativeness of the data collection objects and the rationality of their spatial distribution. At the same time, it collects necessary instrument transformer attribute information to support data tracing and node modeling.

[0070] Step S102: Based on the high-precision optical fiber communication module, the voltage signal output from the secondary side of the voltage transformer is synchronously acquired with a unified time reference. The voltage signal comes from the transformation output of the bus, incoming or outgoing voltage measured by the voltage transformer in actual operation, forming structured raw voltage data.

[0071] Step S102 completes the high-precision, unified time-base synchronous acquisition of the output voltage signals of each voltage transformer, ensuring that the multi-source data has alignment and time consistency in time series analysis, and records the sampling results in a structured manner.

[0072] Step S103: Upload the structured raw voltage data to the time series database to complete the format standardization conversion and field validation.

[0073] Step S103 standardizes the storage of raw voltage data and verifies the validity of fields, ensuring accuracy, consistency and traceability in subsequent data processing.

[0074] Step S1 is used to establish a synchronous data acquisition system for multiple voltage transformers in the substation, forming a data foundation with a unified time reference and structured standards, providing raw voltage data support for subsequent error analysis and model construction.

[0075] Step S2 includes the following sub-steps:

[0076] Step S201: Extract the physical voltage nodes corresponding to the voltage transformers in the substation and construct a logical connection diagram.

[0077] Step S201 clarifies the identity of the physical voltage nodes connected to each voltage transformer and constructs an electrical connection diagram between the nodes, providing topological information for subsequent voltage function modeling.

[0078] Step S202: Based on the logical relationship of the electrical nodes connected to the voltage transformer, analyze the voltage conduction path between the bus, incoming line and outgoing line, and construct a reference voltage function model.

[0079] The reference voltage function model includes the voltage relationships, transformer ratios, and coupling effects between each physical voltage node.

[0080] Step S202 extracts the conduction structure in each voltage path according to the node logical relationship, constructs a function model reflecting the voltage distribution and transformer relationship between the bus, incoming line and outgoing line, and establishes the mathematical expression of the voltage dependence and coupling effect of each node.

[0081] Step S203: Collect historical operating data. The historical operating data includes the original voltage measurement data of the voltage transformers in multiple time periods, the corresponding substation operating condition information, and the actual load characteristics.

[0082] Based on the regular deviations, coordinated change trends, and static and dynamic relationships between node voltages in historical operating data, and combined with a preset rule set, which includes node voltage stability criteria, load regulation modes, and grid operating status classification rules, a virtual reference voltage generation model is constructed to fit the reference voltage. The virtual reference voltage generation model outputs estimated values ​​based on the comparison between the current node structure and historical patterns.

[0083] Step S203 systematically collects historical operating data from multiple time periods, including raw voltage data, load characteristics and operating conditions. Combining the coordinated change trends and voltage response patterns between nodes, a virtual reference voltage generation model is trained according to preset rules to achieve structured error learning capability.

[0084] Step S204: Fit the current original voltage data using a virtual reference voltage generation model, and output a virtual reference voltage sequence that matches the actual nodes.

[0085] The reference voltage function model supports a dynamic parameter adaptive adjustment mechanism, which includes:

[0086] The type of topology change is determined based on the real-time collected operating status.

[0087] When a topology change event occurs, the node function parameters are recalculated and updated to the reference voltage function model.

[0088] Parameters are adjusted through incremental learning.

[0089] Indicators of coordinated change trends include:

[0090] Calculate the average rate of change of error within a sliding window to identify short-term fluctuation trends.

[0091] The rate of change of short-term fluctuations is extracted by second-order difference of the mean.

[0092] The drift slope is extracted as a long-term trend indicator by fitting the mean trajectory of the error using the least squares method.

[0093] Short-term fluctuation trends, short-term fluctuation rate of change, and long-term trend indicators are used as feature variables for state classification and scoring.

[0094] Step S204 inputs the raw voltage measurement data at the current moment into the trained virtual reference voltage generation model, fits and outputs a virtual reference voltage sequence that matches the actual electrical node structure, and uses it as the reference value source for subsequent error calculation. The reference voltage function model has dynamic parameter adaptive capability, and can automatically identify the type of structural change according to the real-time monitored topology changes, reconstruct the function parameters and update the model through incremental learning, so as to achieve adaptive response to changes in the operating environment and maintain estimation accuracy.

[0095] Step S2 is used to construct a virtual reference voltage generation mechanism that can dynamically reflect the electrical structure characteristics and historical operating patterns of the substation. By integrating node voltage relationships, historical measurement characteristics and expert rules, it outputs virtual reference voltage data with timing accuracy and structural adaptability, providing a benchmark sequence with high comparability and strong dynamic response capability for voltage transformer error assessment.

[0096] Step S3 includes the following sub-steps:

[0097] Step S301: Compare the original voltage measurement data with the virtual reference voltage sequence to generate a measurement error sequence.

[0098] Step S301 compares the difference between the original voltage measurement data of each voltage transformer at the current moment and the corresponding virtual reference voltage value, and outputs a measurement error sequence representing the change in error amplitude at each time point, thus establishing a basic data source for error feature extraction.

[0099] Step S302: Perform sliding window segmentation statistics on the measurement error sequence, extract the mean, extreme range, variance and rate of change of the error, and output the voltage transformer error statistical feature data.

[0100] Step S302 performs sliding window segmentation processing on the measurement error sequence, extracts key statistical indicators within each window segment, including the mean error, extreme range, variance, and rate of change, to form structured voltage transformer error statistical characteristic data for subsequent state assessment.

[0101] Step S303: Based on the classification criteria, a comprehensive analysis is performed on the statistical characteristic data of voltage transformer errors within each sliding time window. The logic of the comprehensive analysis is as follows:

[0102] The voltage transformer error statistical characteristic data is compared with the preset state classification standard. Based on the performance of the voltage transformer error statistical characteristic data on the preset state classification standard, the operating state level of the corresponding voltage transformer in the corresponding time window is marked and output. The operating state level includes normal, slight abnormality, moderate abnormality and severe abnormality.

[0103] Step S303 compares and analyzes the extracted error statistical feature data with the system's preset status grading standard. Based on the position of each indicator in the grading standard, it comprehensively determines the operating status level of the voltage transformer within the current time window and marks it as normal, slightly abnormal, moderately abnormal, or severely abnormal. The status level result is output for subsequent scoring and early warning modules to call.

[0104] Step S3 is used to dynamically extract the error change characteristics of the voltage transformer based on the comparative analysis between the original voltage measurement data and the virtual reference voltage, and to identify its operating status level in combination with the status grading standard, so as to provide data support and classification basis for subsequent health scoring and early warning strategies.

[0105] Step S4 includes the following sub-steps:

[0106] Step S401: Identify the periodic changes, continuous shifts, and sudden anomalies in the voltage transformer error statistical data, and construct an error feature mapping table.

[0107] Step S401 extracts time series change patterns from error statistical feature data, identifies representative periodic changes, persistent shifts and sudden anomalies, constructs an error feature mapping table, and provides input data sources for scoring factors.

[0108] Step S402: Referring to historical voltage error data and a preset scoring model, the scoring model is constructed based on the aforementioned voltage transformer error statistical characteristic data. Independent scoring factor weights are set for different feature dimensions, and the corresponding health factor score values ​​are calculated after normalization.

[0109] Obtain health factor scores, perform weighted summation of health factor scores according to the weighted calculation rules set in the scoring model, and output a comprehensive health score result.

[0110] Step S402 involves inputting the extracted error features into a preset scoring model. The scoring model sets weights based on dimensions such as mean error, extreme range, variance, and rate of change. After normalizing each indicator, the corresponding health factor score is calculated. Then, all factor scores are combined using weighted rules to output a comprehensive health score that reflects the operating status of the voltage transformer.

[0111] Step S403: When the comprehensive health score is lower than the preset warning threshold, the warning mechanism is triggered and a maintenance task signal is generated.

[0112] The logic of step S403 is as follows:

[0113] Continuously compare the health scores and thresholds of the current transformers.

[0114] When the score is below the threshold, an inspection suggestion of the corresponding level is generated according to the scheduling rules.

[0115] Optimize the scheduling scheme by combining the location of the current transformer, voltage level, and maintenance records.

[0116] Output maintenance scheduling suggestions and upload them to the operation and maintenance platform for the generation of work assignment instructions.

[0117] Step S403 continuously compares the output comprehensive health score with the warning threshold set by the system; if the score is lower than the warning threshold, the warning mechanism is triggered according to the built-in scheduling rules, and a preliminary inspection suggestion including the inspection priority level and suggested response cycle is generated; combined with the actual installation location, voltage level and historical maintenance records of the transformer, the maintenance scheduling path and resource allocation scheme are dynamically optimized, and finally the maintenance scheduling suggestion is generated and uploaded to the operation and maintenance platform for automatic generation and execution of work orders.

[0118] Step S4 is used to identify the operating status evolution mode of the voltage transformer based on error statistical characteristics, construct a health scoring model and dynamically output the comprehensive scoring result, and link the early warning and maintenance scheduling mechanism when the scoring result is abnormal, thus completing the closed-loop transformation from error identification to proactive maintenance.

[0119] Step S5 includes the following sub-steps:

[0120] Step S501: Receive log feedback information, which includes inspection time, equipment number, inspection judgment label, and on-site remarks.

[0121] The log feedback information is compared one by one with the voltage transformer error statistical feature data and operating status level to identify sample pairs that are consistent with and inconsistent with the voltage transformer error statistical feature data. The comparison results are output and a difference comparison report is generated based on the comparison results. The difference comparison report includes the consistency ratio, the reason for the difference, and the scope of impact.

[0122] Step S501 receives log feedback information from the operation and maintenance terminal or monitoring system, including equipment number, inspection time, manual judgment label and on-site record. The feedback information is compared with the operating status level previously output by the system based on error statistical characteristics, and consistent and inconsistent sample pairs are identified. Based on the comparison results, a difference comparison report is output. The report indicates the consistency ratio, possible sources of deviation and their affected areas, which is used to evaluate the system accuracy and potential correction needs.

[0123] Step S502: The sample pairs that are determined to be consistent are labeled as reliable training samples and input into the model training process of the error classification model and the virtual reference voltage generation model.

[0124] For sample pairs with inconsistent status labels, they are submitted to the expert system interface for manual verification and labeling, and high-confidence samples are output. These high-confidence samples are then input into the model training process of the error classification model and the virtual reference voltage generation model.

[0125] Step S502 identifies the sample pairs marked as consistent in the comparison as reliable samples and inputs them as high-quality training samples into the training process of the error classification model and the virtual reference voltage generation model to improve the model accuracy. For sample pairs with inconsistent labels, they are submitted to the expert system interface for manual verification and correction labeling. The confirmed samples are then input into the model training process again as high-confidence samples to further enhance the robustness and generalization ability of the model in abnormal sample identification and complex scenarios.

[0126] Step S5 is used to construct a closed-loop self-optimization mechanism for the voltage transformer error assessment system. By comparing and analyzing the consistency between the operation and maintenance inspection feedback and the system identification results, high-quality samples are selected for model iteration training to continuously improve the accuracy and adaptability of the error identification and estimation model.

[0127] Step S6 includes the following sub-steps:

[0128] Step S601: The measurement error sequence, comprehensive health score results, and operating status are used to construct error line charts, score trend charts, and equipment level distribution charts, respectively. The line charts, score trend charts, and equipment level distribution charts are then converted to a unified format and visualized.

[0129] Step S601 uses the measurement error sequence, comprehensive health score result, and operating status level obtained in the previous steps as input data to generate error line charts, score trend charts, and equipment level distribution charts, respectively. The charts reflect the dynamic changes in error of each voltage transformer, the results of operating stability assessment, and the overall status distribution. After generation, all types of charts are uniformly converted into data formats that meet the access requirements of the system visualization module, completing the format standardization process before graphic rendering.

[0130] Step S602: Upload the line chart, rating trend chart, and equipment level distribution chart to the client platform.

[0131] Step S602 uploads the formatted chart data to the client interactive platform for operation and maintenance personnel to view and compare in real time. The platform supports functions such as chart switching, node filtering, and historical trend backtracking, enabling synchronous sharing of analysis results between local terminals and remote operation and maintenance systems, thereby improving the efficiency of early warning response and scheduling deployment.

[0132] Step S6 is used to display the voltage transformer error assessment results in a unified graphical manner, thereby enhancing the operation and maintenance personnel's intuitive perception of error change trends and equipment status, and uploading the chart data to the client platform to support the visual linkage between remote operation and maintenance decision-making and equipment status monitoring.

[0133] This invention eliminates the need for external physical standards. By constructing a virtual reference voltage generation model, it dynamically estimates a high-precision benchmark using operational data, effectively solving the problem of traditional methods relying on manual comparison and standard equipment. By introducing node voltage logic, historical collaborative characteristics, and operational rules, it enhances the model's ability to adapt to complex substation topologies. It extracts error feature data using a sliding window and outputs equipment status levels based on preset grading standards, enabling the differentiation and location of errors of different severity. Based on error statistical indicators, it constructs a health scoring model, outputs a comprehensive score value, and dynamically generates inspection tasks and maintenance suggestions by linking the score with early warning thresholds. It integrates inspection feedback and expert verification samples to continuously iterate and train the error identification and reference estimation model, improving the system's self-learning ability and evaluation accuracy. It converts error evolution trends, scoring results, and status levels into charts and uploads them to the client, facilitating intuitive judgment and assisting scheduling decisions by operation and maintenance personnel.

[0134] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. These 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 function 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 function specified in one or more boxes.

[0135] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for evaluating the metering error of a voltage transformer, characterized in that, Includes the following steps: Step S1: Construct a synchronous acquisition system for multiple voltage transformers within the substation to obtain raw voltage data; Step S2: Construct a virtual reference voltage generation model and output a reference voltage sequence; Step S3: Calculate the error statistical characteristics and label the voltage transformer operating status level; Step S4: Evaluate the health score based on the error characteristics and output the score result; Step S5: Receive inspection feedback, compare differences, and update the model; Step S6: Generate analysis charts and upload them to the client for display and linkage with the operation and maintenance system; Step S2 includes the following sub-steps: Step S201: Extract the physical voltage nodes corresponding to the voltage transformers in the substation and construct a logical connection diagram; Step S202: Based on the logical relationship of the electrical nodes connected to the voltage transformer, analyze the voltage conduction path between the bus, incoming line and outgoing line, and construct a reference voltage function model; The reference voltage function model includes the voltage relationship, transformer ratio, and coupling effects between each physical voltage node; Step S203: Collect historical operating data, which includes the original voltage measurement data of the voltage transformers in multiple time periods, the corresponding substation operating condition information, and the actual load characteristics. Based on the regular deviations, coordinated change trends, and static and dynamic relationships between node voltages in historical operating data, and combined with a preset rule set, which includes node voltage stability criteria, load regulation modes, and grid operating status classification rules, a virtual reference voltage generation model is constructed to fit the reference voltage. The virtual reference voltage generation model outputs an estimated value based on the comparison between the current node structure and historical patterns. Step S204: Fit the current original voltage data using a virtual reference voltage generation model, and output a virtual reference voltage sequence that matches the actual nodes; The reference voltage function model supports a dynamic parameter adaptive adjustment mechanism, which includes: Determine the type of topology change based on real-time collected operational status data; When a topology change event occurs, the node function parameters are recalculated and updated to the reference voltage function model; Adjust parameters through incremental learning; The indicators of the coordinated change trend include: Calculate the average rate of change of error within a sliding window to identify short-term fluctuation trends; The rate of change of short-term fluctuations is extracted by second-order difference of the mean. The drift slope is extracted as a long-term trend indicator by fitting the mean error trajectory using the least squares method. Short-term fluctuation trends, short-term fluctuation rate of change, and long-term trend indicators are used as feature variables for state classification and scoring.

2. The method for evaluating the metering error of a voltage transformer as described in claim 1, characterized in that, Step S1 includes the following sub-steps: Step S101: Select multiple voltage transformers installed at specific busbar, incoming line and outgoing line locations in the substation as monitoring objects, covering the main voltage node areas, and record the installation point, operation number and electrical node information corresponding to each voltage transformer. Step S102: Based on the high-precision optical fiber communication module, the voltage signal output from the secondary side of the voltage transformer is synchronously acquired with a unified time reference. The voltage signal comes from the transformation output of the bus, incoming or outgoing voltage measured by the voltage transformer in actual operation, forming structured raw voltage data. Step S103: Upload the structured raw voltage data to the time series database to complete the format standardization conversion and field validation.

3. The method for evaluating the metering error of a voltage transformer as described in claim 2, characterized in that, Step S3 includes the following sub-steps: Step S301: Compare the original voltage measurement data with the virtual reference voltage sequence to generate a measurement error sequence; Step S302: Perform sliding window segmentation statistics on the measurement error sequence, extract the mean, extreme range, variance and rate of change of the error, and output the voltage transformer error statistical feature data. Step S303: Based on the classification criteria, a comprehensive analysis is performed on the statistical characteristic data of the voltage transformer error within each sliding time window. The logic of the comprehensive analysis is as follows: The voltage transformer error statistical characteristic data is compared with the preset state classification standard. Based on the performance of the voltage transformer error statistical characteristic data on the preset state classification standard, the operating state level of the corresponding voltage transformer in the corresponding time window is marked and output. The operating state level includes normal, slightly abnormal, moderately abnormal and severely abnormal.

4. The method for evaluating the metering error of a voltage transformer as described in claim 3, characterized in that, Step S4 includes the following sub-steps: Step S401: Identify the periodic changes, continuous shifts, and sudden anomalies in the voltage transformer error statistical characteristic data, and construct an error characteristic mapping table; Step S402: Refer to historical voltage error data and a preset scoring model. The scoring model is constructed based on the aforementioned voltage transformer error statistical characteristic data. Independent scoring factor weights are set for different characteristic dimensions. After normalization processing, the corresponding health factor score values ​​are calculated respectively. Obtain health factor scores, perform weighted summation of health factor scores according to the weighted calculation rules set in the scoring model, and output a comprehensive health score result; Step S403: When the comprehensive health score is lower than the preset warning threshold, the warning mechanism is triggered and a maintenance task signal is generated.

5. The method for evaluating the metering error of a voltage transformer as described in claim 4, characterized in that, The logic of step S403 is as follows: Continuously compare the health scores and thresholds of the current transformers; When the score is below the threshold, an inspection suggestion of the corresponding level is generated according to the scheduling rules; Optimize the scheduling plan by combining the location of the current transformer, voltage level, and maintenance records; Output maintenance scheduling suggestions and upload them to the operation and maintenance platform for the generation of work assignment instructions.

6. The method for evaluating the metering error of a voltage transformer as described in claim 5, characterized in that, Step S5 includes the following sub-steps: Step S501: Receive log feedback information, which includes inspection time, equipment number, inspection judgment label and on-site remarks. The log feedback information is compared one by one with the voltage transformer error statistical feature data and the operating status level. The sample pairs that are consistent with the voltage transformer error statistical feature data and the sample pairs that are inconsistent are identified, the comparison results are output, and a difference comparison report is generated based on the comparison results. The difference comparison report includes the consistency ratio, the reason for the difference and the scope of the impact. Step S502: Label the sample pairs that are determined to be consistent as reliable training samples and input them into the model training process of the error classification model and the virtual reference voltage generation model. For sample pairs with inconsistent status labels, they are submitted to the expert system interface for manual verification and labeling, and high-confidence samples are output. These high-confidence samples are then input into the model training process of the error classification model and the virtual reference voltage generation model.

7. The method for evaluating the metering error of a voltage transformer as described in claim 6, characterized in that, Step S6 includes the following sub-steps: Step S601: Construct error line charts, scoring trend charts, and equipment level distribution charts from the measurement error sequence, comprehensive health score results, and operating status, respectively. The line charts, scoring trend charts, and equipment level distribution charts are then visualized and displayed after being converted to a unified format. Step S602: Upload the line chart, rating trend chart, and equipment level distribution chart to the client platform.

Images