Method and device for online discrimination of metering performance of station-end electric energy metering device

Through high-precision sensors and multivariate correlation analysis model, combined with signal-to-noise ratio and filtering technology, the problem of insufficient multivariate correlation analysis in online discrimination of station-end power metering devices is solved, and the accuracy and robustness of metering performance discrimination are improved. Ensure data quality and reliability of discriminant results.

CN119064852APending Publication Date: 2024-12-03YILI RIVER POWER SUPPLY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411197329.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-29
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The existing online discrimination method of the station-end power metering device has limitations in multivariate correlation analysis, and it is impossible to fully consider the complex relationship between different parameters, and the unstable data quality affects the accuracy of the discrimination results.

Method used

High-precision sensors are used for data acquisition and regular calibration, data repetitive sampling technology is used to reduce random errors, design multivariate correlation analysis model to learn variable relationships through linear regression model, combine signal-to-noise ratio and total harmonic distortion to evaluate data quality, and use digital filtering The device removes noise, designs discriminant rules and thresholds to evaluate the severity of abnormalities, and updates the model through continuous learning and adaptive algorithms.

Benefits of technology

It improves the accuracy and robustness of metering performance discrimination, can capture complex multivariable relationships in the data more accurately, enhances the ability to detect metering performance abnormalities, and ensures data quality stability and reliability of discriminative results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119064852A_ABST
    Figure CN119064852A_ABST
Patent Text Reader

Abstract

The invention provides a method and a device for online discrimination of metering performance of a station-end electric energy metering device. According to the metering performance online discrimination method and device for the station end electric energy metering device, S1, a high-precision sensor is used for collecting data, regular calibration is carried out, and it is ensured that the collected data has accuracy and stability; according to the on-line discrimination method and device for the metering performance of the station-end electric energy metering device, data are collected through a high-precision sensor, regular calibration is carried out, the accuracy and stability of the collected data are ensured, a multivariable correlation analysis model is designed, and the accuracy and stability of the data are ensured. According to the method, a complex multivariable relation in data is captured, characteristics are used as input variables, metering performance indexes are used as output variables, and metering performance abnormity is judged by taking a multivariable correlation analysis model as a linear regression model, so that the problems that the quality of the acquired data is unstable and multivariable correlation analysis is insufficient are solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of online determination of metering performance of electric energy metering devices, and in particular to an online determination method and device for metering performance of a station-side electric energy metering device. Background Art

[0002] Online determination of the metering performance of the power metering device at the station refers to analyzing and evaluating the real-time data of the power metering device to determine whether its metering performance is normal or abnormal. This online determination can help the detection system operator to promptly discover problems with the metering device and take appropriate measures to repair or replace it to ensure the accuracy and reliability of the metering data. The following are some commonly used methods and indicators for online determination of the metering performance of the power metering device at the station: Meeting accuracy requirements: The accuracy of the power metering device is an important indicator for evaluating its metering performance. Online determination can check whether the metering device is within the allowable error range by comparing it with the preset accuracy requirements. Data continuity and stability: The metering device should be able to provide continuous and stable data output. Online determination can detect the continuity and stability of the data and identify whether there are problems such as data interruption, jump or abnormal fluctuation. Frequency and phase measurement: The power metering device usually needs to accurately measure the frequency and phase information of the voltage and current. Online determination can verify the difference between these measured values ​​and the standard frequency and phase to determine the frequency and phase measurement performance of the metering device. Power measurement: The power metering device should be able to accurately measure parameters such as active power, reactive power and apparent power. Online identification can compare the power value measured by the metering device with the expected value of the actual load or other reference values ​​to detect whether there is a deviation or abnormality. Calibration and verification: Regular calibration and verification of electric energy metering devices is an important step to ensure their metering performance. Online identification can monitor the time of the last calibration and verification, and provide alarms or reminders to ensure that the metering device is maintained and repaired as planned. Anomaly detection: By establishing an anomaly detection model based on historical data and pattern recognition algorithms, abnormal conditions of electric energy metering devices can be identified online. These anomalies may include data anomalies, sensor failures, or calculation algorithm errors.

[0003] However, current energy metering involves correlation analysis between multiple parameters and variables, such as voltage, current, power factor, etc. The current online discrimination method may have certain limitations in multivariate correlation analysis and cannot fully consider the complex relationship between different parameters. In addition, the accuracy and reliability of online discrimination are affected by the quality of the collected data. If there is a fault or transmission error in the data acquisition system, it will affect the accuracy of the discrimination result. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a method and device for online determination of the metering performance of a station-side electric energy metering device, which solves the problems of unstable quality of collected data and insufficient multivariate correlation analysis.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: including:

[0006] S1. Use high-precision sensors to collect data and perform regular calibration to ensure the accuracy and stability of the collected data. Then introduce data repeated sampling technology, take multiple samples and take the average value to reduce the impact of random errors on data quality.

[0007] S2. Use signal-to-noise ratio and total harmonic distortion to evaluate the stability and accuracy of data acquisition quality. When the data quality does not meet the standard, use a digital filtering algorithm to filter the collected data to remove high-frequency noise and interference. The filtering uses an IIR filter. The metering performance indicators are power factor, current distortion, frequency deviation, frequency stability, instantaneous voltage change, and harmonic distortion. The digital filtering algorithm is specifically a low-pass filter.

[0008] S3. Design a multivariate association analysis model to capture the complex multivariate relationship in the data. Take the features as input variables and the measurement performance indicators as output variables. Train the model to learn the association between variables. The multivariate association analysis model is a linear regression model. The linear regression model is expressed as:

[0009] y=w1x1+w2x2+…+w n × n +b

[0010] Among them, y is the measurement performance index, x1, x2, …, x n are input variables, w1,w2,…,w n is the weight parameter of the model, and b is the bias parameter of the model;

[0011] By training the model and determining the values ​​of weight parameters and bias parameters, the metrological performance indicator y can be predicted and compared with the actual observed values ​​to evaluate the metrological performance.

[0012] S4. Use discrimination rules and thresholds to evaluate the severity of abnormal metering performance, determine the error range, degree of fluctuation, degree of deviation from standard values, and judge whether the metering performance meets the predetermined requirements. The discrimination rules include absolute threshold discrimination, relative threshold discrimination, and level division. The level division divides the degree of abnormality into multiple levels, and formulates corresponding discrimination rules and thresholds according to different levels. For example, the voltage deviation is divided into three levels: slight, medium and severe, and different thresholds are set according to different levels to judge the degree of abnormality.

[0013] S5. When abnormal metering performance is detected, which includes abnormal electric energy metering, abnormal current quality, abnormal frequency quality and abnormal power quality, the identification system generates corresponding alarm information, including sending alarm notification to relevant personnel, generating alarm log and triggering feedback mechanism, and the triggering feedback mechanism is specifically to automatically shut down the circuit.

[0014] S6. Design user interfaces and visualization tools, and display real-time data, identification results, and alarm information to facilitate monitoring and analysis.

[0015] S7. Introduce continuous learning and adaptive algorithms, continuously update the discrimination model and parameters to adapt to changes in data characteristics and system evolution, call historical data, use historical data for model verification, and combine multivariate association analysis models for calibration and optimization to improve the accuracy and robustness of metrological performance discrimination.

[0016] Further:

[0017] The filtering adopts an IIR filter, and the metering performance indicators are power factor, current distortion, frequency deviation, frequency stability, instantaneous voltage change, and harmonic distortion.

[0018] Further:

[0019] The alarm information includes sending an alarm notification to relevant personnel, generating an alarm log and triggering a feedback mechanism, wherein the triggering feedback mechanism is specifically an automatic circuit shutdown.

[0020] Further:

[0021] The multivariate association analysis model is a linear regression model, which is expressed as:

[0022] y=w1x1+w2x2+…+w n × n +b

[0023] Among them, y is the measurement performance index, x1, x2, …, x n are input variables, w1,w2,…,w n is the weight parameter of the model, and b is the bias parameter of the model.

[0024] Further:

[0025] The discrimination rules in step S4 include absolute threshold discrimination, relative threshold discrimination, and level division.

[0026] Further:

[0027] The metering performance abnormalities include electric energy metering abnormalities, current quality abnormalities, frequency quality abnormalities, and power quality abnormalities.

[0028] Further:

[0029] The digital filtering algorithm is specifically a low-pass filter.

[0030] Further:

[0031] A device for online determination of metering performance of a station-side electric energy metering device, comprising a data collector, a communication module, a data processor, a user interface and a visualization tool module, and a storage and display module. The data collector is electrically connected to the processor, the communication module is electrically connected to the processor, the user interface and the visualization tool module are electrically connected to the storage and display module, the data collector comprises a temperature sensor, a pressure sensor, a humidity sensor, and an acceleration sensor, and the data processor comprises an analog-to-digital converter, an amplifier, and a filter;

[0032] Further:

[0033] The data collector comprises a temperature sensor, a pressure sensor, a humidity sensor and an acceleration sensor.

[0034] The data of the data collector is connected to the user interface and the visualization tool module via the data processor and the communication module, and is stored in the storage display module.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] The online discrimination method of the metering performance of the station-side electric energy metering device collects data through high-precision sensors and performs regular calibration to ensure the accuracy and stability of the collected data. A multivariate association analysis model is designed to capture the complex multivariate relationship in the data, and the features are used as input variables and the metering performance indicators are used as output variables. The multivariate association analysis model is converted into a linear regression model to discriminate metering performance anomalies, thereby solving the problems of unstable quality of collected data and insufficient multivariate association analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a step diagram of the discrimination method of the present invention;

[0038] Figure 2 It is a schematic diagram of the device module of the present invention. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] like Figure 1 As shown, an embodiment of the present invention provides a method for online determination of metering performance of a station-side electric energy metering device, comprising the following steps:

[0041] S1. Use high-precision sensors to collect data and perform regular calibration to ensure the accuracy and stability of the collected data. Then introduce data repeated sampling technology, take multiple samples and take the average value to reduce the impact of random errors on data quality;

[0042] S2. Use signal-to-noise ratio and total harmonic distortion to evaluate the stability and accuracy of data acquisition quality. When the data quality does not meet the standards, use a digital filtering algorithm to filter the collected data to remove high-frequency noise and interference;

[0043] S3. Design a multivariate association analysis model to capture the complex multivariate relationships in the data, use features as input variables, measure performance indicators as output variables, and train the model to learn the associations between variables;

[0044] S4. Use discrimination rules and thresholds to evaluate the severity of measurement performance anomalies, determine the error range, degree of fluctuation, degree of deviation from the standard value, and determine whether the measurement performance meets the predetermined requirements;

[0045] S5. When abnormal metering performance is detected, the discrimination system generates corresponding alarm information;

[0046] S6. Design user interfaces and visualization tools, and display real-time data, identification results, and alarm information to facilitate monitoring and analysis;

[0047] S7. Introduce continuous learning and adaptive algorithms, continuously update the discrimination model and parameters to adapt to changes in data characteristics and system evolution, call historical data, use historical data for model verification, and combine multivariate association analysis models for calibration and optimization to improve the accuracy and robustness of metrological performance discrimination.

[0048] The filtering adopts an IIR filter, and the metering performance indicators are power factor, current distortion, frequency deviation, frequency stability, instantaneous voltage change, and harmonic distortion.

[0049] The alarm information includes sending an alarm notification to relevant personnel, generating an alarm log and triggering a feedback mechanism, wherein the triggering feedback mechanism is specifically an automatic circuit shutdown.

[0050] The multivariate association analysis model is a linear regression model, which is expressed as:

[0051] y=w1x1+w2x2+…+w n ×n +b

[0052] Among them, y is the measurement performance index, x1, x2, …, x n are input variables, w1,w2,…,w n is the weight parameter of the model, and b is the bias parameter of the model.

[0053] w n is the weight parameter of the model, b is the bias parameter of the model. By training the model and determining the values ​​of the weight parameter and the bias parameter, the metrological performance index y can be predicted and compared with the actual observed value to evaluate the metrological performance.

[0054] The discrimination rules in step S4 include absolute threshold discrimination, relative threshold discrimination, and level division. The level division divides the abnormality degree into multiple levels, and corresponding discrimination rules and thresholds are formulated according to different levels.

[0055] The metering performance abnormalities include electric energy metering abnormalities, current quality abnormalities, frequency quality abnormalities, and power quality abnormalities.

[0056] The digital filtering algorithm is specifically a low-pass filter.

[0057] like Figure 2 As shown, it is a schematic diagram of the module structure of the device of the present invention, including a data collector, a communication module, a data processor, a user interface and visualization tool module, and a storage and display module. The data collector is electrically connected to the processor, the communication module is electrically connected to the processor, the user interface and visualization tool module is electrically connected to the storage and display module, the data collector includes a temperature sensor, a pressure sensor, a humidity sensor, and an acceleration sensor, the data processor includes an analog-to-digital converter, an amplifier, and a filter; the data collector includes a temperature sensor, a pressure sensor, a humidity sensor, and an acceleration sensor.

[0058] The data of the data collector is connected to the user interface and the visualization tool module via the data processor and the communication module, and is stored in the storage display module.

[0059] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for online determination of the metering performance of a station-side electric energy metering device. Features: The following steps are involved: S1. Use high-precision sensors to collect data and perform regular calibration to ensure the accuracy and stability of the collected data. Then introduce data repeated sampling technology, take multiple samples and take the average value; S2. Use signal-to-noise ratio and total harmonic distortion to evaluate the stability and accuracy of data acquisition quality. When the data quality does not meet the standards, use a digital filtering algorithm to filter the collected data to remove high-frequency noise and interference; S3. Design a multivariate association analysis model to capture the complex multivariate relationships in the data, use features as input variables, measure performance indicators as output variables, and train the model to learn the associations between variables; S4. Use discrimination rules and thresholds to evaluate the severity of measurement performance anomalies, determine the error range, degree of fluctuation, degree of deviation from the standard value, and determine whether the measurement performance meets the predetermined requirements; S5. When abnormal metering performance is detected, the discrimination system generates corresponding alarm information; S6. Design user interface and visualization tools, and display real-time data, identification results and alarm information; S7. Introduce continuous learning and adaptive algorithms, continuously update the discrimination model and parameters to adapt to changes in data characteristics and system evolution, call historical data, use historical data for model verification, and combine multivariate association analysis models for calibration and optimization to improve the accuracy and robustness of metrological performance discrimination.

2. According to claim 1, a method for online determination of metering performance of a station-side electric energy metering device is characterized in that: The filtering adopts an IIR filter, and the metering performance indicators are power factor, current distortion, frequency deviation, frequency stability, instantaneous voltage change, and harmonic distortion.

3. The method for online determination of metering performance of a station-side electric energy metering device according to claim 1 is characterized in that: The alarm information includes sending an alarm notification to relevant personnel, generating an alarm log and triggering a feedback mechanism, wherein the triggering feedback mechanism is specifically an automatic circuit shutdown.

4. The method for online determination of metering performance of a station-side electric energy metering device according to claim 1 is characterized in that: The multivariate association analysis model is a linear regression model, which is expressed as: y=w1x1+w2x2+…+w n ×x n +b Among them, y is the measurement performance index, x1, x2, …, x n are input variables, w1,w2,…,w n is the weight parameter of the model, and b is the bias parameter of the model.

5. The method for online determination of metering performance of a station-side electric energy metering device according to claim 1 is characterized in that: The discrimination rules in step S4 include absolute threshold discrimination, relative threshold discrimination, and level division.

6. The method for online determination of metering performance of a station-side electric energy metering device according to claim 1, characterized in that: The metering performance abnormalities include electric energy metering abnormalities, current quality abnormalities, frequency quality abnormalities, and power quality abnormalities.

7. The method for online determination of metering performance of a station-side electric energy metering device according to claim 1, characterized in that: The digital filtering algorithm is specifically a low-pass filter.

8. According to claim 1, a method for online determination of metering performance of a station-side electric energy metering device, Features: The following steps are performed using the device as described in any one of claims 1 to 7: It includes a data collector, a communication module, a data processor, a user interface and a visualization tool module, and a storage and display module. The data collector is electrically connected to the processor, the communication module is electrically connected to the processor, the user interface and the visualization tool module are electrically connected to the storage and display module, the data collector includes a temperature sensor, a pressure sensor, a humidity sensor, and an acceleration sensor, and the data processor includes an analog-to-digital converter, an amplifier, and a filter.

9. The online determination device for measuring performance of a station-side electric energy metering device according to claim 8, characterized in that: The data collector comprises a temperature sensor, a pressure sensor, a humidity sensor and an acceleration sensor.

10. The online determination device for measuring performance of a station-side electric energy metering device according to claim 8, Features: The data of the data collector is connected to the user interface and the visualization tool module via the data processor and the communication module, and is stored in the storage display module.