A method and system for adaptive calibration of electric energy meter

By constructing a performance degradation model and utilizing sensor data, adaptive calibration of electricity meters is achieved, solving the problem of the inability to monitor the performance degradation of electricity meters in real time, ensuring the long-term accuracy and reliability of electricity meters, and improving calibration efficiency.

CN118688709BActive Publication Date: 2024-11-01NANJING METER TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411171205.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-26
Publication Date
2024-11-01
Estimated Expiration
2044-08-26

AI Technical Summary

Technical Problem

Existing technology cannot monitor the performance degradation of electricity meters in real time, resulting in the inability to calibrate in a timely manner and affecting the accuracy of electricity metering.

Method used

By acquiring basic and supplementary data from the electricity meter, aligning time-series data and dividing periods, constructing a performance degradation model, and using sensors to collect environmental data, adaptive calibration results are generated, enabling adaptive calibration management of the electricity meter.

Benefits of technology

This enables effective calibration management of electricity meters, ensuring their long-term accuracy and reliability, and improving the efficiency of calibration work.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118688709B_ABST
    Figure CN118688709B_ABST
Patent Text Reader

Abstract

The present application provides an adaptive calibration method and system for an electric energy meter, and relates to the technical field of electric energy meter calibration. The method includes: obtaining basic data and additional data of the electric energy meter, performing time series data alignment, and periodizing the environmental data set to generate a time series segmentation result, obtaining device information of the electric energy meter, performing feature key analysis within the period, establishing interference weight factors of each feature, constructing a performance attenuation model, collecting the use environment data of the electric energy meter through monitoring sensors, and then generating adaptive calibration results according to the performance attenuation model, and finally performing electric energy meter calibration management. The present application can solve the technical problem that the prior art cannot monitor the attenuation of the performance of the electric energy meter in real time, resulting in the inability to calibrate in time, further affecting the accuracy of electric energy metering, and realizes effective calibration management of the electric energy meter, ensures the long-term accuracy and reliability of the electric energy meter, and improves the efficiency of calibration work.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of electric meter calibration, and in particular to an electric energy meter adaptive calibration method and system. Background Art

[0002] During long-term use, the measurement error of the energy meter may gradually increase due to various factors, such as temperature changes, humidity, electromagnetic interference, mechanical wear, etc., affecting the accuracy of measurement. Traditional calibration methods usually require the energy meter to be removed from the site of use and sent to a special calibration laboratory. This method is time-consuming and labor-intensive, and may cause additional damage to the energy meter during the disassembly and assembly process. In addition, due to the long calibration cycle, the error of the energy meter between two calibrations may accumulate, affecting the accuracy of measurement.

[0003] In summary, the prior art has a technical problem in which the attenuation of the performance of the electric energy meter cannot be monitored in real time, resulting in the inability to calibrate in time, further affecting the accuracy of electric energy measurement. Summary of the invention

[0004] The purpose of this application is to provide an adaptive calibration method and system for an electric energy meter, so as to solve the technical problem that the prior art cannot monitor the attenuation of the electric energy meter performance in real time, resulting in the inability to calibrate in time, further affecting the accuracy of electric energy measurement, thereby realizing effective calibration management of the electric energy meter, ensuring the long-term accuracy and reliability of the electric energy meter, and improving the efficiency of the calibration work.

[0005] In view of the above problems, the present application provides an electric energy meter adaptive calibration method and system.

[0006] In a first aspect, the present application provides an adaptive calibration method for an electric energy meter, which is implemented by an adaptive calibration system for an electric energy meter, wherein the method comprises: obtaining basic data and additional data of the electric energy meter, wherein the basic data is log data of the electric energy meter, and the additional data comprises an environmental data set and known calibration data; performing time series data alignment of the basic data and the additional data, and periodically dividing the environmental data set, segmenting the time series data alignment result according to the periodic division result, and generating a time series segmentation result; obtaining device information of the electric energy meter, performing feature key analysis within the period on the time series segmentation result based on the device information, and establishing interference weight factors of each feature; constructing a performance attenuation model, and optimizing parameters within the performance attenuation model through the time series segmentation result, wherein the performance attenuation model is as follows: ;in, is the performance decay function, , , The time The weighting factors of temperature, humidity and electromagnetic interference under is the initial performance level, is the base of natural logarithm, is the time attenuation coefficient, is a time variable, representing the cumulative time from the beginning of performance decay, is the integral variable, representing the range from 0 to At any point in time within the time period, Characterization temperature In time The impact function on performance, Characterizing humidity In time The impact function on performance, Characterization of electromagnetic In time The invention discloses an impact function on performance; collects the use environment data of the electric energy meter through monitoring sensors and constructs a sensor data set; inputs the sensor data set into a performance attenuation model after parameter optimization to generate an adaptive calibration result; and performs calibration management of the electric energy meter through the adaptive calibration result.

[0007] In the second aspect, the present application also provides an electric energy meter adaptive calibration system for executing an electric energy meter adaptive calibration method as described in the first aspect, wherein the system includes: a data acquisition module, the data acquisition module is used to acquire basic data and additional data of the electric energy meter, the basic data is the log data of the electric energy meter, and the additional data includes an environmental data set and known calibration data; a timing segmentation result generation module, the timing segmentation result generation module is used to perform timing data alignment of the basic data and the additional data, and to divide the environmental data set into periods, and to divide the timing data alignment results according to the period division results to generate timing segmentation results; a feature key analysis module, the feature key analysis module is used to acquire device information of the electric energy meter, and to perform feature key analysis within the period on the timing segmentation results based on the device information, and to establish interference weight factors of each feature; a model construction module, the model construction module is used to construct a performance attenuation model, and to optimize parameters within the performance attenuation model through the timing segmentation results, wherein the performance attenuation model is as follows: ;in, is the performance decay function, , , The time The weighting factors of temperature, humidity and electromagnetic interference under is the initial performance level, is the base of natural logarithm, is the time attenuation coefficient, is a time variable, representing the cumulative time from the beginning of performance decay, is an integral variable, representing the range from 0 to At any point in time within the time period, Characterization temperature In time The impact function on performance, Characterizing humidity In time The impact function on performance, Characterization of electromagnetic In time A function affecting performance; a sensor data set construction module, the sensor data set construction module is used to collect the use environment data of the electric energy meter through monitoring sensors and construct a sensor data set; an adaptive calibration result generation module, the adaptive calibration result generation module is used to input the sensor data set into the performance attenuation model after parameter optimization, and generate an adaptive calibration result; a calibration management module, the calibration management module is used to perform electric energy meter calibration management through the adaptive calibration result.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] By acquiring basic data and additional data of the electric energy meter, the basic data is the log data of the electric energy meter, and the additional data includes an environmental data set and known calibration data; performing time series data alignment of the basic data and the additional data, and performing period division on the environmental data set, segmenting the time series data alignment result according to the period division result, and generating a time series segmentation result; acquiring device information of the electric energy meter, performing feature key analysis within the period on the time series segmentation result based on the device information, and establishing interference weight factors of various features; constructing a performance attenuation model, and optimizing parameters within the performance attenuation model through the time series segmentation result, wherein the performance attenuation model is as follows: ;in, is the performance decay function, , , The time The weighting factors of temperature, humidity and electromagnetic interference under is the initial performance level, is the base of natural logarithm, is the time attenuation coefficient, is a time variable, representing the cumulative time from the beginning of performance decay, is an integral variable, representing the range from 0 to At any point in time within the time period, Characterization temperature In time The impact function on performance, Characterizing humidity In time The impact function on performance, Characterization of electromagnetic In time The invention relates to an influencing function of performance; collecting the use environment data of the electric energy meter by monitoring sensors and constructing a sensor data set; inputting the sensor data set into the performance attenuation model after parameter optimization and generating an adaptive calibration result; and performing calibration management of the electric energy meter by using the adaptive calibration result, thereby effectively solving the technical problem that the prior art cannot monitor the attenuation of the performance of the electric energy meter in real time, resulting in the inability to calibrate in time, further affecting the accuracy of electric energy measurement, and realizing effective calibration management of the electric energy meter, thereby ensuring the long-term accuracy and reliability of the electric energy meter and improving the efficiency of the calibration work.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0012] Figure 1 A flowchart of an adaptive calibration method for an electric energy meter is provided in the present application.

[0013] Figure 2 This is a schematic diagram of the structure of an electric energy meter adaptive calibration system for the present application.

[0014] Description of reference numerals:

[0015] Data acquisition module 11, time series segmentation result generation module 12, feature key analysis module 13, model construction module 14, sensor data set construction module 15, adaptive calibration result generation module 16, calibration management module 17. DETAILED DESCRIPTION

[0016] The present application provides an adaptive calibration method and system for an electric energy meter, thereby solving the technical problem in the prior art that the electric energy meter cannot be calibrated in time due to the inability to monitor the attenuation of the electric energy meter performance in real time, which further affects the accuracy of electric energy measurement. The application realizes effective calibration management of the electric energy meter, ensures the long-term accuracy and reliability of the electric energy meter, and improves the efficiency of the calibration work.

[0017] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0018] Embodiment 1

[0019] Please see attached Figure 1 The present application provides an electric energy meter adaptive calibration method, wherein the method is applied to an electric energy meter adaptive calibration system, and the method specifically comprises the following steps:

[0020] S1: Acquire basic data and additional data of an electric energy meter, wherein the basic data is log data of the electric energy meter, and the additional data includes an environmental data set and known calibration data.

[0021] Specifically, basic data refers to various data recorded by the energy meter during operation, including energy readings, the total energy consumption recorded by the energy meter; power data, real-time or time-divided power consumption data; voltage and current data, real-time or time-divided voltage and current readings. Event logs refer to any abnormal events recorded by the energy meter, such as voltage fluctuations, current overloads, etc. Additional data provides information on external factors that affect the performance of the energy meter, including environmental data sets, such as temperature, humidity, electromagnetic interference and other environmental factors; known calibration data refers to the data of historical calibration of the energy meter, including calibration time, calibration results, etc., which are used to compare and verify the accuracy of the model.

[0022] Regularly read the log data of the energy meter through the communication interface of the energy meter, such as RS-485, wireless communication, etc. Install temperature, humidity sensors and electromagnetic interference detectors at the installation location of the energy meter to collect environmental data regularly.

[0023] S2: Execute time series data alignment of the basic data and the additional data, and periodize the environment data set, segment the time series data alignment result according to the periodicity division result, and generate a time series segmentation result.

[0024] Specifically, time series data alignment is to match data from different sources in chronological order to ensure that the meter readings at each time point have corresponding environmental data during analysis. Ensure that the meter log data and environmental monitoring data are accurately timestamped. If the data sampling rates of the meter and environmental data are different, adjust or interpolate them to align them at the same time point. Use data processing tools or programming languages, such as data frames in Python, R, such as Pandas, to align the data to ensure that the meter readings at each time point have corresponding environmental data. Periodic partitioning is to divide the continuous environmental data set into certain periods, such as days, weeks, months, etc., so as to analyze the changes in the performance of the meter in different periods. Determine the granularity of periodic partitioning according to the analysis requirements. For example, if you want to analyze the impact of seasonal changes on the meter, you can choose to partition by month. Use data processing tools or functions in programming languages ​​to partition the data according to the determined time period. Analyze the impact of environmental factors on the performance of the meter and the changing trend of the meter performance in each period. The result of time series partitioning is to partition the aligned data according to the results of periodic partitioning to generate a series of data fragments with the same time period. The aligned data set is segmented according to the results of period division, and each data segment contains the electric energy meter log data and environmental data within a complete period. The segmented data segments are stored as new data sets.

[0025] S3: Acquire device information of the electric energy meter, perform key feature analysis within a period on the time series segmentation result based on the device information, and establish interference weight factors of various features.

[0026] Specifically, the equipment information includes the type, model, manufacturer, age, historical maintenance records, calibration history, etc. of the energy meter, and the equipment information is queried through the equipment management system. Feature key analysis refers to analyzing the key factors of the performance degradation of the energy meter and determining the importance of these factors in the performance degradation. These features include environmental factors such as temperature, humidity, electromagnetic interference, etc. Frequency of use, the frequency of use of the energy meter and the load mode. Aging degree The age and aging degree of the energy meter. Use statistical methods or machine learning algorithms to analyze the time series segmentation results and identify the main features that affect the performance of the energy meter. Calculate the correlation between different features and the performance degradation of the energy meter to determine which features are critical. Based on the correlation analysis results, select the features that have the greatest impact on the performance of the energy meter for analysis. The interference weight factor quantifies the degree to which each feature affects the performance degradation. Use regression analysis, principal component analysis, and other methods to automatically determine the weights based on the data. Train machine learning models, such as random forests or gradient boosting machines, to allow the model to automatically learn the weights of features.

[0027] S4: Construct a performance degradation model, and optimize the parameters in the performance degradation model according to the time series segmentation result, wherein the performance degradation model is as follows:

[0028] ;

[0029] in, is the performance decay function, , , The time The weighting factors of temperature, humidity and electromagnetic interference under is the initial performance level, is the base of natural logarithm, is the time attenuation coefficient, is a time variable, representing the cumulative time from the beginning of performance decay, is the integral variable, representing the range from 0 to At any point in time within the time period, Characterization temperature In time The impact function on performance, Characterizing humidity In time The impact function on performance, Characterization of electromagnetic In time Impact function on performance.

[0030] Specifically, building a performance degradation model can take into account the initial performance level of the electric energy meter, time variables, and environmental factors such as temperature, humidity, and electromagnetic interference. Using the time series segmentation results, prepare a training data set, including time, performance level, temperature, humidity, electromagnetic interference and other data. Use machine learning libraries such as scikit-learn, TensorFlow, PyTorch, etc. to train the performance degradation model. Use statistical methods such as least squares or machine learning algorithms such as gradient descent to estimate model parameters. Use a portion of the data that is not involved in the training to verify the accuracy of the model, and avoid overfitting through methods such as cross-validation. Adjust the model parameters based on the verification results, and repeat the estimation and verification process until the model reaches a satisfactory accuracy. By building and optimizing the performance degradation model, the performance changes of the electric energy meter in the future can be more accurately predicted, thereby providing a basis for the adaptive calibration of the electric energy meter.

[0031] S5: Collect the usage environment data of the electric energy meter through monitoring sensors and build a sensor data set.

[0032] Specifically, according to the environmental impacts that the energy meter may be subject to, select appropriate sensors to monitor key environmental parameters. For example, temperature sensors, humidity sensors, and electromagnetic interference sensors. Temperature sensors are used to monitor temperature changes around the energy meter. Humidity sensors are used to monitor changes in air humidity. Electromagnetic interference sensors are used to monitor the strength and changes of electromagnetic fields. The selected sensors are installed near the energy meter to ensure that the sensors can accurately capture the environmental conditions that affect the performance of the energy meter. The installation location of the sensor should be representative of the actual use environment of the energy meter. The sensor collects environmental data periodically or in real time. The frequency of data collection depends on the type of sensor and the needs of analysis. For temperature and humidity sensors, data is collected every few minutes to hours; for electromagnetic interference sensors, data is collected more frequently. The collected data is stored in a database or data lake to build a sensor data collection.

[0033] S6: Inputting the sensing data set into the performance decay model after parameter optimization to generate an adaptive calibration result.

[0034] Specifically, any outliers or erroneous data are removed, the data is converted to a specific format, and normalized or standardized. The data set is split into training, validation, and test sets to evaluate the performance of the model. The prepared sensor data set is input into the performance degradation model. The input to the model typically includes time series data, as well as environmental factors related to the performance of the energy meter, such as temperature, humidity, and electromagnetic interference. The input data is processed using the model to generate predictions of performance degradation. These results may include the expected performance level of the energy meter at a specific point in the future, or the rate at which performance degrades. Based on the model's predictions, instructions or recommendations for adaptive calibration are generated. These results include calibration requirement indications to determine when the energy meter needs to be calibrated. The calibration adjustment calculates the calibration amount that needs to be adjusted to compensate for performance degradation.

[0035] S7: Performing calibration management of the electric energy meter based on the adaptive calibration result.

[0036] Specifically, analyze the adaptive calibration results to determine whether the energy meter needs to be calibrated, as well as the urgency and importance of the calibration. According to the calibration results, formulate a calibration plan, including the calibration schedule, resource allocation, and workflow. Preferably, determine the equipment and personnel resources to perform the calibration, and select a suitable calibration method, such as remote calibration or on-site calibration, to reduce the impact of the calibration on the user's electricity consumption, such as selecting off-peak hours for calibration. Perform the calibration of the energy meter according to the calibration plan. Including sending a calibration command to the energy meter through a remote communication system. Or dispatching a technician to the site to perform the calibration operation. Record the details of the calibration, including the calibration date, calibration personnel, and calibration results.

[0037] Furthermore, step S4 of the present application also includes:

[0038] A temperature abnormality threshold is established based on the device information; and a temperature influence function is constructed through the temperature abnormality threshold, as follows: ;in, is the temperature influence function, is the temperature abnormality threshold, is the first adaptive adjustment coefficient, is the second adaptive adjustment coefficient, is the adjustment constant; a performance attenuation model is constructed according to the temperature influence function.

[0039] Specifically, the temperature abnormality threshold refers to the critical value at which the temperature exceeds the normal operating range, resulting in abnormal performance of the energy meter. This threshold can be determined based on historical performance data and field test results. Analyze the historical temperature data and the corresponding energy meter performance data to find the temperature points where the performance is significantly reduced, and refer to the temperature impact guide provided by the energy meter manufacturer. Conduct field tests to determine the changes in the performance of the energy meter at a specific temperature. The temperature impact function describes the specific impact of temperature changes on the performance of the energy meter. Use statistical methods or machine learning algorithms to determine the parameters in the function, such as adaptive adjustment coefficients and adjustment constants. Verify the effectiveness of the function by comparing predicted and actual data, and adjust the parameters as needed. Integrating the temperature impact function into the performance degradation model can more accurately predict the impact of temperature changes on the performance of the energy meter. Use the temperature impact function as a component in the performance degradation model. Use historical data to train the model and use the validation data set to evaluate the accuracy of the model.

[0040] Furthermore, the present application also includes:

[0041] Construct the electromagnetic interference impact function as follows: ;in, is the electromagnetic interference influence function, is a logarithmic coefficient, representing the impact of electromagnetic interference on performance in the first stage. is the logarithmic function growth rate parameter, which characterizes the sensitivity of performance degradation when electromagnetic interference increases. is the exponential pre-coefficient, which is used to characterize the impact of electromagnetic interference on performance in the second stage. is the adjustment parameter of the exponential decay rate, Characterize the electromagnetic interference intensity; and construct a performance attenuation model through the electromagnetic interference influence function and the temperature influence function.

[0042] Specifically, collect the electromagnetic interference data of the environment where the electric energy meter is located, including the strength and frequency of the electromagnetic field, and record the performance data of the electric energy meter under different electromagnetic interference conditions, and analyze the relationship between the electromagnetic interference strength and the performance of the electric energy meter. Use statistical methods or machine learning algorithms to determine the parameters in the electromagnetic interference impact function, such as logarithmic coefficients, growth rate parameters, pre-coefficients, and attenuation rate adjustment parameters. Combine the electromagnetic interference impact function with the previously constructed temperature impact function to build a more comprehensive performance attenuation model. This model will consider the impact of temperature and electromagnetic interference on the performance of the electric energy meter at the same time. Use actual data to verify the accuracy of the model, and adjust the model parameters based on the verification results to improve the prediction ability of the model.

[0043] Furthermore, the present application also includes:

[0044] Record a calibration data set of an electric energy meter, wherein the calibration data set stores an adaptive calibration result in time series; perform an adaptive calibration scale evaluation based on the calibration data set, and construct a supervisory test cycle based on the evaluation result, wherein the supervisory test cycle carries a test frequency identifier; perform calibration verification of the electric energy meter through the supervisory test cycle, and generate calibration feedback; and perform model optimization of a performance attenuation model based on the calibration feedback.

[0045] Specifically, the calibration data set contains detailed information about each calibration, including the calibration date, calibration results, calibration equipment used, technicians who performed the calibration, etc. Ensure that the calibration data set can be stored in time sequence and use a database or data management system to store and manage calibration data. Adaptive calibration scale evaluation is a quantitative assessment of the calibration effect of the energy meter, which can help determine the frequency and calibration strategy of calibration. Define evaluation criteria, such as accuracy and stability after calibration. Analyze the calibration data set to evaluate the effect of each calibration. The supervision test cycle is a cycle of testing and verification of the energy meter within a specified time to ensure that it continues to meet performance requirements. Determine the frequency of supervision testing based on the results of the adaptive calibration scale evaluation. Plan a schedule for supervision testing, including daily testing, periodic testing, and special testing. Calibration verification is the actual test of the energy meter through the supervision test cycle to verify the effect of calibration. Perform performance tests on the energy meter according to the supervision test cycle. Record test results, including test data, test conditions, and test personnel. Generate calibration feedback based on the test results, including the effectiveness of calibration, existing problems, and recommended improvement measures. Based on the calibration feedback, optimize the performance degradation model to improve its prediction accuracy and adaptability. Adjust model parameters based on calibration feedback and integrate new calibration data into the model for future training and prediction. Use machine learning techniques to let the model learn from new data and continuously optimize its performance.

[0046] Furthermore, the present application also includes:

[0047] Based on the equipment information, a cumulative warning threshold for environmental anomalies is constructed; the cumulative anomalies of the environment are calculated through the sensor data set; an abnormal trigger judgment is made on the cumulative anomaly calculation result through the environmental anomaly cumulative warning threshold; if the abnormal trigger judgment result is a trigger result, an abnormal warning for the electric energy meter is generated, and the electric energy meter maintenance and management is performed according to the abnormal warning for the electric energy meter.

[0048] Specifically, the cumulative warning threshold of environmental anomalies refers to the warning standard that triggers abnormal performance of the electric energy meter when the cumulative impact of environmental factors, such as temperature, humidity, and electromagnetic interference, exceeds a certain limit. Analyze historical environmental data and electric energy meter performance data to determine the cumulative impact of environmental factors on the performance of the electric energy meter. The warning threshold is set by technical personnel in this field and dynamically adjusted according to the actual operation situation. By analyzing the sensor data set, the cumulative anomalies of environmental factors are calculated to evaluate their potential impact on the performance of the electric energy meter. Clean and process the sensor data to ensure data quality and consistency. Use statistical methods or machine learning algorithms to evaluate the cumulative impact of environmental factors. Compare the cumulative anomaly calculation results with the warning threshold to determine whether an anomaly is triggered. Compare the cumulative anomaly calculation results with the warning threshold. Set the judgment logic, such as when the cumulative anomaly exceeds the threshold, trigger the abnormal warning. If the abnormal trigger judgment result is triggered, generate an abnormal warning of the electric energy meter. Generate an early warning message, including the electric energy meter identification, abnormal description, recommended actions, etc. Notify the maintenance team in time through SMS, email or maintenance system. Perform maintenance management of the electric energy meter based on the abnormal warning of the electric energy meter. According to the early warning information, a maintenance plan is formulated and technicians are dispatched to conduct on-site inspections and necessary maintenance operations.

[0049] Furthermore, the present application also includes:

[0050] If the abnormal trigger judgment result is a non-triggering result, an environmental abnormality feature is established according to the cumulative abnormality calculation result; an abnormality cumulative analysis is performed through the environmental abnormality feature to generate a cumulative abnormality constraint; optimization compensation of the performance attenuation model after parameter optimization is performed based on the cumulative abnormality constraint, and the adaptive calibration result is updated according to the optimization compensation result.

[0051] Specifically, even if the anomaly is not triggered, environmental anomaly features are still established based on the cumulative anomaly calculation results to track the changing trend of environmental factors. Key features, such as the fluctuation range and change rate of environmental factors, are extracted from the cumulative anomaly calculation results, and the extracted features are represented as numerical values ​​or vectors that can be used for subsequent analysis. Cumulative anomaly analysis is performed through environmental anomaly features to generate cumulative anomaly constraints to predict possible environmental anomalies in the future. A prediction model is established using statistical methods or machine learning algorithms to predict the cumulative anomaly trend of environmental factors. Based on the prediction results, the constraints of the cumulative anomaly are determined, that is, under what conditions the cumulative impact of environmental factors may exceed the warning threshold. Based on the cumulative anomaly constraints, the performance attenuation model after parameter optimization is optimized and compensated to improve the model's adaptability to environmental anomalies. According to the cumulative anomaly constraints, the model parameters, such as the adaptive adjustment coefficient and the attenuation rate adjustment parameter, are adjusted. The adjusted model is verified using a new data set to ensure its prediction accuracy. According to the results of the optimized and compensated performance attenuation model, the adaptive calibration results are updated to reflect the impact of environmental anomalies on the performance of the electric energy meter. According to the optimized compensation results, the adaptive calibration adjustment amount is calculated, and the adaptive calibration results are updated, including the calibration adjustment amount and the calibration frequency.

[0052] Furthermore, the present application also includes:

[0053] An adaptive maintenance cycle is set; if the adaptive calibration results are all normal calibration results, an adaptive maintenance instruction is activated in the adaptive maintenance cycle; and periodic maintenance of the electric energy meter is performed through the adaptive maintenance instruction.

[0054] Specifically, the adaptive maintenance cycle is a maintenance cycle dynamically set based on the performance decay model and environmental monitoring data of the energy meter. The performance decay model is used to predict the maintenance needs of the energy meter. The environmental factors such as temperature, humidity, and electromagnetic interference are considered to affect the maintenance cycle. The maintenance cycle is dynamically adjusted according to the actual operation and maintenance feedback. If the adaptive calibration results are all normal calibration results, that is, the performance of the energy meter is within the acceptable range, the adaptive maintenance instruction is activated within the adaptive maintenance cycle. The latest adaptive calibration result data is collected, including the performance parameters and environmental data of the energy meter. The calibration results are analyzed using data analysis tools such as Excel and Python to compare the performance changes of the energy meter before and after calibration. According to the preset standards, whether the performance of the energy meter is stable and whether further calibration or maintenance is required is evaluated, and a calibration result analysis report is generated, including the analysis process, evaluation results, and suggestions. According to the adaptive maintenance cycle prediction results, the maintenance cycle that the energy meter should currently perform is determined. According to the performance evaluation results of the energy meter, specific maintenance instructions are formulated, including maintenance content, maintenance personnel, maintenance tools, etc.

[0055] In summary, the electric energy meter adaptive calibration method provided by the present application has the following technical effects:

[0056] By acquiring basic data and additional data of the electric energy meter, the basic data is the log data of the electric energy meter, and the additional data includes an environmental data set and known calibration data; performing time series data alignment of the basic data and the additional data, and performing period division on the environmental data set, segmenting the time series data alignment result according to the period division result, and generating a time series segmentation result; acquiring device information of the electric energy meter, performing feature key analysis within the period on the time series segmentation result based on the device information, and establishing interference weight factors of various features; constructing a performance attenuation model, and optimizing parameters within the performance attenuation model through the time series segmentation result, wherein the performance attenuation model is as follows: ;in, is the performance decay function, , , The time The weighting factors of temperature, humidity and electromagnetic interference under is the initial performance level, is the base of natural logarithm, is the time attenuation coefficient, is a time variable, representing the cumulative time from the beginning of performance decay, is the integral variable, representing the range from 0 to At any point in time within the time period, Characterization temperature In time The impact function on performance, Characterizing humidity In time The impact function on performance, Characterization of electromagnetic In time The invention relates to an influencing function of performance; collecting the use environment data of the electric energy meter by monitoring sensors and constructing a sensor data set; inputting the sensor data set into the performance attenuation model after parameter optimization and generating an adaptive calibration result; and performing calibration management of the electric energy meter by using the adaptive calibration result, thereby effectively solving the technical problem that the prior art cannot monitor the attenuation of the performance of the electric energy meter in real time, resulting in the inability to calibrate in time, further affecting the accuracy of electric energy measurement, and realizing effective calibration management of the electric energy meter, thereby ensuring the long-term accuracy and reliability of the electric energy meter and improving the efficiency of the calibration work.

[0057] Embodiment 2

[0058] Based on the same inventive concept as the electric energy meter adaptive calibration method in the aforementioned embodiment, the present application also provides an electric energy meter adaptive calibration system, see the attached Figure 2 , the system comprising:

[0059] The data acquisition module 11 is used to acquire basic data and additional data of the electric energy meter, wherein the basic data is the log data of the electric energy meter, and the additional data includes an environmental data set and known calibration data.

[0060] The time series segmentation result generation module 12 is used to perform time series data alignment of the basic data and the additional data, and to periodically divide the environmental data set, and to segment the time series data alignment result according to the periodic division result to generate a time series segmentation result.

[0061] The feature key analysis module 13 is used to obtain the equipment information of the electric energy meter, perform feature key analysis within a period on the time series segmentation result based on the equipment information, and establish an interference weight factor of each feature.

[0062] The model building module 14 is used to build a performance degradation model, and optimize the parameters in the performance degradation model according to the time series segmentation result, wherein the performance degradation model is as follows:

[0063] ;

[0064] in, is the performance decay function, , , The time The weighting factors of temperature, humidity and electromagnetic interference under is the initial performance level, is the base of natural logarithm, is the time attenuation coefficient, is a time variable, representing the cumulative time from the beginning of performance decay, is the integral variable, representing the range from 0 to At any point in time within the time period, Characterization temperature In time The impact function on performance, Characterizing humidity In time The impact function on performance, Characterization of electromagnetic In time Impact function on performance.

[0065] The sensor data set building module 15 is used to collect the usage environment data of the electric energy meter through monitoring sensors to build a sensor data set.

[0066] The adaptive calibration result generating module 16 is used to input the sensing data set into the performance attenuation model after parameter optimization to generate an adaptive calibration result.

[0067] The calibration management module 17 is used to manage the calibration of the electric energy meter according to the adaptive calibration result.

[0068] Furthermore, the model building module 14 in the system is also used for:

[0069] A temperature abnormality threshold is established based on the device information; and a temperature influence function is constructed through the temperature abnormality threshold, as follows: ;in, is the temperature influence function, is the temperature abnormality threshold, is the first adaptive adjustment coefficient, is the second adaptive adjustment coefficient, is the adjustment constant; a performance attenuation model is constructed according to the temperature influence function.

[0070] Furthermore, the system further comprises an interference influence function construction module, wherein the interference influence function construction module is used for:

[0071] Construct the electromagnetic interference impact function as follows: ;in, is the electromagnetic interference influence function, is a logarithmic coefficient, representing the impact of electromagnetic interference on performance in the first stage. is the logarithmic function growth rate parameter, which characterizes the sensitivity of performance degradation when electromagnetic interference increases. is the exponential pre-coefficient, which is used to characterize the impact of electromagnetic interference on performance in the second stage. is the adjustment parameter of the exponential decay rate, Characterize the electromagnetic interference intensity; and construct a performance attenuation model through the electromagnetic interference influence function and the temperature influence function.

[0072] Furthermore, the system further comprises a model optimization module, wherein the model optimization module is used to:

[0073] Record a calibration data set of an electric energy meter, wherein the calibration data set stores an adaptive calibration result in time series; perform an adaptive calibration scale evaluation based on the calibration data set, and construct a supervisory test cycle based on the evaluation result, wherein the supervisory test cycle carries a test frequency identifier; perform calibration verification of the electric energy meter through the supervisory test cycle, and generate calibration feedback; and perform model optimization of a performance attenuation model based on the calibration feedback.

[0074] Furthermore, the system further comprises a maintenance management module, wherein the maintenance management module is used to:

[0075] Based on the equipment information, a cumulative warning threshold for environmental anomalies is constructed; the cumulative anomalies of the environment are calculated through the sensor data set; an abnormal trigger judgment is made on the cumulative anomaly calculation result through the environmental anomaly cumulative warning threshold; if the abnormal trigger judgment result is a trigger result, an abnormal warning for the electric energy meter is generated, and the electric energy meter maintenance and management is performed according to the abnormal warning for the electric energy meter.

[0076] Furthermore, the system further comprises a calibration result updating module, wherein the calibration result updating module is used for:

[0077] If the abnormal trigger judgment result is a non-triggering result, an environmental abnormality feature is established according to the cumulative abnormality calculation result; an abnormality cumulative analysis is performed through the environmental abnormality feature to generate a cumulative abnormality constraint; optimization compensation of the performance attenuation model after parameter optimization is performed based on the cumulative abnormality constraint, and the adaptive calibration result is updated according to the optimization compensation result.

[0078] Furthermore, the system further comprises a periodic maintenance module, wherein the periodic maintenance module is used for:

[0079] An adaptive maintenance cycle is set; if the adaptive calibration results are all normal calibration results, an adaptive maintenance instruction is activated in the adaptive maintenance cycle; and periodic maintenance of the electric energy meter is performed through the adaptive maintenance instruction.

[0080] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The energy meter adaptive calibration method and specific examples in the first embodiment are also applicable to the energy meter adaptive calibration system in the present embodiment. Through the above detailed description of the energy meter adaptive calibration method, those skilled in the art can clearly know the energy meter adaptive calibration system in the present embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0081] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0082] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. A method for adaptive calibration of an electric energy meter, characterized in that: The method comprises: Acquire basic data and additional data of the electric energy meter, wherein the basic data is log data of the electric energy meter, and the additional data includes an environmental data set and known calibration data; Execute time series data alignment of the basic data and the additional data, and periodize the environment data set, and segment the time series data alignment result according to the periodicity division result to generate a time series segmentation result; Acquire device information of the electric energy meter, perform key feature analysis within a period on the time series segmentation result based on the device information, and establish interference weight factors of various features; A performance degradation model is constructed, and parameters in the performance degradation model are optimized according to the time series segmentation result, wherein the performance degradation model is as follows: ; in, is the performance decay function, , , The time The weighting factors of temperature, humidity and electromagnetic interference under is the initial performance level, is the base of natural logarithm, is the time attenuation coefficient, is a time variable, representing the cumulative time from the beginning of performance decay, is the integral variable, representing the range from 0 to At any point in time within the time period, Characterization temperature In time Temperature effect on performance as a function of Characterizing humidity In time The impact function on performance, Characterization of electromagnetic In time Electromagnetic interference effect function on performance; Collect the usage environment data of the electric energy meter through monitoring sensors and build a sensor data set; Inputting the sensor data set into the performance decay model after parameter optimization to generate an adaptive calibration result; Performing energy meter calibration management through the adaptive calibration result; Constructing a performance degradation model also includes: Establishing a temperature abnormality threshold based on the device information; The temperature influence function is constructed by the temperature abnormality threshold as follows: ; in, is the temperature influence function, is the temperature abnormality threshold, is the first adaptive adjustment coefficient, is the second adaptive adjustment coefficient, is the adjustment constant; Constructing a performance degradation model according to the temperature impact function; Construct the electromagnetic interference impact function as follows: ; in, is the electromagnetic interference influence function, is a logarithmic coefficient, representing the impact of electromagnetic interference on performance in the first stage. is the logarithmic function growth rate parameter, which characterizes the sensitivity of performance degradation when electromagnetic interference increases. is the exponential pre-coefficient, which is used to characterize the impact of electromagnetic interference on performance in the second stage. is the adjustment parameter of the exponential decay rate, Characterize the intensity of electromagnetic interference; A performance degradation model is constructed by using the electromagnetic interference influence function and the temperature influence function.

2. The method according to claim 1, characterized in that The method further comprises: Recording a calibration data set of the electric energy meter, wherein the calibration data set stores adaptive calibration results in a time sequence; Performing an adaptive calibration scale evaluation based on the calibration data set, and constructing a supervisory test cycle based on the evaluation result, wherein the supervisory test cycle has a test frequency identifier; Performing calibration verification of the electric energy meter through the supervisory test cycle and generating calibration feedback; Model optimization of the performance decay model is performed based on the calibration feedback.

3. The method according to claim 1, characterized in that The method further comprises: Establishing a cumulative warning threshold for environmental anomalies based on the device information; Calculate the accumulated anomalies of the environment through the sensor data set; Perform abnormal triggering judgment on the accumulated abnormal calculation result by using the accumulated warning threshold of environmental abnormality; If the abnormal trigger determination result is a trigger result, an abnormal warning of the electric energy meter is generated, and the electric energy meter maintenance management is performed according to the abnormal warning of the electric energy meter.

4. The method according to claim 3, characterized in that The abnormal triggering determination of the accumulated abnormal calculation result by using the accumulated environmental abnormality warning threshold also includes: If the abnormal trigger determination result is a non-trigger result, establishing an environmental abnormality feature according to the accumulated abnormality calculation result; Performing anomaly accumulation analysis based on the environmental anomaly characteristics to generate cumulative anomaly constraints; The performance attenuation model is optimized and compensated based on the accumulated abnormal constraints after parameter optimization, and the adaptive calibration result is updated according to the optimization and compensation result.

5. The method according to claim 1, characterized in that The method further comprises: Set adaptive maintenance cycles; If the adaptive calibration results are all normal calibration results, activating the adaptive maintenance instruction in the adaptive maintenance period; The periodic maintenance of the electric energy meter is performed through the adaptive maintenance instruction.

6. An adaptive calibration system for electric energy meters, characterized in that: For implementing the steps of the method according to any one of claims 1 to 5, the system comprises: A data acquisition module, wherein the data acquisition module is used to acquire basic data and additional data of the electric energy meter, wherein the basic data is log data of the electric energy meter, and the additional data includes an environmental data set and known calibration data; A time series segmentation result generation module, the time series segmentation result generation module is used to perform time series data alignment of the basic data and the additional data, and to periodically divide the environmental data set, and to segment the time series data alignment result according to the periodic division result to generate a time series segmentation result; A feature key analysis module, the feature key analysis module is used to obtain device information of the electric energy meter, perform feature key analysis within a period on the time series segmentation result based on the device information, and establish an interference weight factor of each feature; A model building module is used to build a performance degradation model, and optimize the parameters in the performance degradation model through the time series segmentation result, wherein the performance degradation model is as follows: ; in, is the performance decay function, , , The time The weighting factors of temperature, humidity and electromagnetic interference under is the initial performance level, is the base of natural logarithm, is the time attenuation coefficient, is a time variable, representing the cumulative time from the beginning of performance decay, is the integral variable, representing the range from 0 to At any point in time within the time period, Characterization temperature In time Temperature effect on performance as a function of Characterizing humidity In time The impact function on performance, Characterization of electromagnetic In time Electromagnetic interference effect function on performance; A sensor data set building module, the sensor data set building module is used to collect usage environment data of the electric energy meter through monitoring sensors to build a sensor data set; An adaptive calibration result generating module, the adaptive calibration result generating module is used to input the sensing data set into the performance decay model after parameter optimization to generate an adaptive calibration result; A calibration management module, the calibration management module is used to perform calibration management of the electric energy meter according to the adaptive calibration result; The model building module is also used to establish a temperature abnormality threshold based on the device information; The temperature influence function is constructed by the temperature abnormality threshold as follows: ; in, is the temperature influence function, is the temperature abnormality threshold, is the first adaptive adjustment coefficient, is the second adaptive adjustment coefficient, is the adjustment constant; Constructing a performance degradation model according to the temperature impact function; Construct the electromagnetic interference impact function as follows: ; in, is the electromagnetic interference influence function, is a logarithmic coefficient, representing the impact of electromagnetic interference on performance in the first stage. is the logarithmic function growth rate parameter, which characterizes the sensitivity of performance degradation when electromagnetic interference increases. is the exponential pre-coefficient, which is used to characterize the impact of electromagnetic interference on performance in the second stage. is the adjustment parameter of the exponential decay rate, Characterize the intensity of electromagnetic interference; A performance degradation model is constructed by using the electromagnetic interference influence function and the temperature influence function.