Adaptive calibration method and system for electric energy meter

Abstract

An adaptive calibration method and system for an electric energy meter, relating to the technical field of electric energy meter calibration. The method comprises: acquiring basic data and additional data of an electric energy meter (S1); performing time series data alignment, and performing period division on an environment data set to generate a time series segmentation result (S2); acquiring device information of the electric energy meter, performing key feature analysis within a period, and establishing an interference weight factor for each feature (S3); building a performance degradation model (S4); acquiring usage environment data of the electric energy meter by means of a monitoring sensor (S5); then generating an adaptive calibration result on the basis of the performance degradation model (S6); and finally performing electric energy meter calibration management (S7). The present invention solves the technical problem in the prior art where the accuracy of electric energy metering is affected due to untimely calibration caused by an inability to monitor performance degradation of an electric energy meter in real time, thereby implementing effective calibration management for the electric energy meter, ensuring the long-term accuracy and reliability of the electric energy meter, and improving the efficiency of calibration work.

Description

An adaptive calibration method and system for electricity meters

[0001] This application claims priority to Chinese Patent Application No. 202411171205.6, filed on August 26, 2024, entitled "An Adaptive Calibration Method and System for an Electricity Meter". Technical Field

[0002] This invention relates to the field of electricity meter calibration technology, and in particular to an adaptive calibration method and system for electricity meters. Background Technology

[0003] Over prolonged use, electricity meters may experience a gradual increase in measurement error due to various factors such as temperature variations, humidity, electromagnetic interference, and mechanical wear, affecting the accuracy of metering. Traditional calibration methods typically require removing the electricity meter from the field and sending it to a specialized calibration laboratory. This method is time-consuming and labor-intensive, and may cause additional damage to the meter during disassembly and reassembly. Furthermore, due to the long calibration cycle, errors may accumulate between two calibrations, affecting the accuracy of metering.

[0004] In summary, existing technologies suffer from the technical problem of being unable to monitor the performance degradation of electricity meters in real time, leading to the inability to calibrate in a timely manner and further affecting the accuracy of electricity metering. Summary of the Invention

[0005] The purpose of this invention is to provide an adaptive calibration method and system for electricity meters, which solves the technical problem that the existing technology cannot monitor the performance degradation of electricity meters in real time, resulting in the inability to calibrate in a timely manner and further affecting the accuracy of electricity metering. This invention enables effective calibration management of electricity meters, ensures the long-term accuracy and reliability of electricity meters, and improves the efficiency of calibration work.

[0006] In view of the above problems, the present invention provides an adaptive calibration method and system for electricity meters.

[0007] In a first aspect, the present invention provides an adaptive calibration method for electricity meters, which is implemented through an adaptive calibration system for electricity meters. The method includes: acquiring basic data and supplementary data of the electricity meter, wherein the basic data is log data of the electricity meter, and the supplementary data includes an environmental dataset and known calibration data; performing time-series data alignment of the basic data and the supplementary data, and periodically dividing the environmental dataset; segmenting the time-series data alignment result according to the periodic division result to generate a time-series segmentation result; acquiring device information of the electricity meter, performing feature key analysis within the period based on the device information on the time-series segmentation result, and establishing interference weight factors for each feature; constructing a performance degradation model, and optimizing the parameters within the performance degradation model using the time-series segmentation result, wherein the performance degradation model is as follows: Wherein, P is the performance degradation function, ωT(s), ωH(s), and ωE(s) are the interference weighting factors of temperature, humidity, and electromagnetic interference at time s, respectively, P0 is the initial performance level, e is the base of the natural logarithm, a is the time degradation coefficient, t is the time variable representing the cumulative time from the start of performance degradation, s is the integral variable representing any time point within the time interval from 0 to t, b(T(s)) represents the influence function of temperature T on performance at time s, c(H(s)) represents the influence function of humidity H on performance at time s, and d(E(s)) represents the influence function of electromagnetic interference E on performance at time s; the usage environment data of the electricity meter is collected by monitoring sensors to construct a sensor data set; the sensor data set is input into the performance degradation model optimized according to the parameters to generate adaptive calibration results; the electricity meter calibration management is performed through the adaptive calibration results.

[0008] Secondly, the present invention also provides an adaptive calibration system for electricity meters, used to execute an adaptive calibration method for electricity meters as described in the first aspect, wherein the system includes: a data acquisition module, used to acquire basic data and supplementary data of the electricity meter, wherein the basic data is log data of the electricity meter, and the supplementary data includes an environmental dataset and known calibration data; a time-series segmentation result generation module, used to perform time-series data alignment of the basic data and the supplementary data, and to perform periodic division of the environmental dataset, 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, used to acquire device information of the electricity meter, and to perform feature key analysis within the period based on the device information on the time-series segmentation result to establish interference weight factors for each feature; and a model building module, used to build a performance degradation model, and to optimize the parameters within the performance degradation model using the time-series segmentation result, wherein the performance degradation model is as follows: Wherein, P is the performance degradation function, ωT(s), ωH(s), and ωE(s) are the interference weighting factors of temperature, humidity, and electromagnetic interference at time s, respectively, P0 is the initial performance level, e is the base of the natural logarithm, a is the time degradation coefficient, t is the time variable representing the cumulative time from the start of performance degradation, s is the integral variable representing any time point within the time interval from 0 to t, b(T(s)) represents the influence function of temperature T on performance at time s, c(H(s)) represents the influence function of humidity H on performance at time s, and d(E(s)) represents the influence function of electromagnetic interference E on performance at time s; a sensor data set construction module is used to collect environmental data of the electricity meter through monitoring sensors and construct a sensor data set; an adaptive calibration result generation module is used to input the sensor data set into the performance degradation model optimized according to parameters to generate adaptive calibration results; and a calibration management module is used to manage the calibration of the electricity meter through the adaptive calibration results.

[0009] One or more technical solutions provided in this invention have at least the following technical effects or advantages:

[0010] By acquiring basic and supplementary data from the electricity meter, where the basic data is the meter's log data and the supplementary data includes an environmental dataset and known calibration data; performing time-series data alignment of the basic and supplementary data, dividing the environmental dataset into periods, and segmenting the time-series data alignment result based on the period division result to generate a time-series segmentation result; acquiring the electricity meter's device information, performing feature key analysis within the period based on the device information, and establishing interference weight factors for each feature; constructing a performance degradation model, and optimizing the parameters within the performance degradation model using the time-series segmentation result, wherein the performance degradation model is as follows:

[0011] Where P is the performance decay function, ωT(s), ωH(s), and ωE(s) are the weighting factors for temperature, humidity, and electromagnetic interference at time s, respectively, P0 is the initial performance level, e is the base of the natural logarithm, a is the time decay coefficient, t is the time variable representing the cumulative time from the start of performance decay, s is the integral variable representing any time point within the time interval from 0 to t, b(T(s)) represents the influence function of temperature T on performance at time s, c(H(s)) represents the influence function of humidity H on performance at time s, and d(E(s)) represents the influence function of electromagnetic interference E on performance at time s. The system incorporates a function to assess the impact of electricity meter performance. It collects environmental data from monitoring sensors to construct a sensor dataset. This dataset is then input into a performance degradation model optimized based on parameters to generate adaptive calibration results. The adaptive calibration results are used for electricity meter calibration management. This effectively solves the technical problem in existing technologies where the inability to monitor electricity meter performance degradation in real time leads to delayed calibration, further affecting the accuracy of electricity metering. The system achieves effective calibration management of electricity meters, ensuring their long-term accuracy and reliability, and improving the efficiency of calibration work.

[0012] The above description is merely an overview of the technical solution of the present invention. To better understand the technical means of the present invention and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of the present invention more apparent, specific embodiments of the present invention are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily apparent from the following description. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0014] Figure 1 is a flowchart illustrating an adaptive calibration method for an energy meter according to the present invention.

[0015] Figure 2 is a schematic diagram of the structure of an adaptive calibration system for an electricity meter according to the present invention.

[0016] Figure labeling: Data acquisition module 11, time series segmentation result generation module 12, feature key analysis module 13, model building module 14, sensor data set construction module 15, adaptive calibration result generation module 16, calibration management module 17. Detailed Implementation

[0017] This invention provides an adaptive calibration method and system for electricity meters, which solves the technical problem in existing technologies where the inability to monitor the performance degradation of electricity meters in real time leads to the inability to calibrate in a timely manner, further affecting the accuracy of electricity metering. It enables effective calibration management of electricity meters, ensures the long-term accuracy and reliability of electricity meters, and improves the efficiency of calibration work.

[0018] The technical solutions of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. It should be understood that the present invention is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention. It should also be noted that, for ease of description, only the parts related to the present invention are shown in the accompanying drawings, not all of them.

[0019] Example 1

[0020] Please refer to Figure 1. This invention provides an adaptive calibration method for electricity meters, wherein the method is applied to an adaptive calibration system for electricity meters, and the method specifically includes the following steps:

[0021] S1: Obtain the basic data and additional data of the electricity meter. The basic data is the log data of the electricity meter, and the additional data includes environmental datasets and known calibration data.

[0022] Specifically, the basic data consists of various data recorded by the electricity meter during operation. This includes electricity readings (total electricity consumption recorded by the meter); power data (real-time or time-segmented power consumption); voltage and current data (real-time or time-segmented voltage and current readings); event logs (any abnormal events recorded by the meter, such as voltage fluctuations or current overloads); and supplementary data (information on external factors affecting meter performance, including environmental datasets such as temperature, humidity, and electromagnetic interference); and known calibration data (historical calibration data of the meter, including calibration time and results, used to compare and verify the model's accuracy).

[0023] The electricity meter's log data is periodically read via its communication interface, such as RS-485 or wireless communication. Temperature and humidity sensors and an electromagnetic interference detector are installed at the electricity meter's installation location to collect environmental data periodically.

[0024] S2: Perform time-series data alignment of the basic data and the supplementary data, and perform periodic partitioning of the environmental dataset. Based on the periodic partitioning result, segment the time-series data alignment result to generate a time-series segmentation result.

[0025] Specifically, time-series data alignment involves matching data from different sources in chronological order to ensure that each meter reading at any given time point in the analysis has corresponding environmental data. It ensures that both meter log data and environmental monitoring data have accurate timestamps. If the sampling rates of meter and environmental data differ, adjustments or interpolation are performed to align them at the same time points. Data alignment is achieved using data processing tools or programming languages, such as Python, R, and data frameworks like Pandas, ensuring that each meter reading at any given time point has corresponding environmental data. Period segmentation involves dividing the continuous environmental dataset according to a specific period, such as days, weeks, or months, to analyze changes in meter performance within different periods. The granularity of period segmentation is determined based on the analytical needs; for example, if analyzing the impact of seasonal changes on meters, monthly segmentation can be chosen. Data segmentation is performed using functions in data processing tools or programming languages ​​based on the defined time period. Within each period, the impact of environmental factors on meter performance and the trends in meter performance are analyzed. The time-series segmentation result is the division of the aligned data according to the period segmentation result, generating a series of data segments with the same time period. The aligned dataset is divided according to the periodic partitioning results. Each data segment contains electricity meter log data and environmental data for a complete period. The segmented data segments are then stored as a new dataset.

[0026] S3: Obtain the device information of the electricity meter, perform feature key analysis within the period based on the device information, and establish interference weight factors for each feature.

[0027] Specifically, equipment information includes the type, model, manufacturer, service life, historical maintenance records, and calibration history of the electricity meter, which can be queried through the equipment management system. Feature-critical analysis refers to analyzing the key factors contributing to the performance degradation of the electricity meter and determining their importance. These features include environmental factors such as temperature, humidity, and electromagnetic interference; usage frequency, including the meter's usage frequency and load pattern; and aging degree, including the meter's service life and aging level. Statistical methods or machine learning algorithms are used to analyze the time-series segmentation results to identify the main features affecting the electricity meter's performance. The correlation between different features and the electricity meter's performance degradation is calculated to determine which features are critical. Based on the correlation analysis results, the features with the greatest impact on the electricity meter's performance are selected for analysis. Interference weighting factors quantify the degree to which each feature affects performance degradation. Regression analysis, principal component analysis, and other methods are used to automatically determine weights based on the data. Machine learning models, such as random forests or gradient boosting machines, are trained to automatically learn the feature weights.

[0028] S4: Construct a performance degradation model, and optimize the parameters within the performance degradation model using the time-series segmentation results. The performance degradation model is as follows:

[0029] Where P is the performance decay function, ωT(s), ωH(s), and ωE(s) are the interference weighting factors of temperature, humidity, and electromagnetic interference at time s, respectively, P0 is the initial performance level, e is the base of the natural logarithm, a is the time decay coefficient, t is the time variable, representing the cumulative time from the start of performance decay, s is the integral variable, representing any time point within the time interval from 0 to t, h(T(s)) represents the influence function of temperature T on performance at time s, c(H(s)) represents the influence function of humidity H on performance at time s, and d(E(s)) represents the influence function of electromagnetic interference E on performance at time s.

[0030] Specifically, constructing a performance degradation model takes into account the initial performance level of the electricity meter, time variables, and environmental factors such as temperature, humidity, and electromagnetic interference. Using time-series segmentation results, a training dataset is prepared, including data on time, performance level, temperature, humidity, and electromagnetic interference. Machine learning libraries such as scikit-learn, TensorFlow, and PyTorch are used to train the performance degradation model. Statistical methods, such as least squares, or machine learning algorithms, such as gradient descent, are used to estimate the model parameters. A subset of data not used in training is used to validate the model's accuracy, and overfitting is avoided through methods such as cross-validation. Based on the validation results, the model parameters are adjusted, and the estimation and validation process is repeated until the model achieves satisfactory accuracy. By constructing and optimizing the performance degradation model, the performance changes of the electricity meter over a future period can be predicted more accurately, thus providing a basis for adaptive calibration of the electricity meter.

[0031] S5: Collect environmental data of electricity meters by monitoring sensors and construct a sensor data set.

[0032] Specifically, based on the environmental influences that the electricity meter may be subject to, appropriate sensors are selected to monitor key environmental parameters. Examples include temperature sensors, humidity sensors, and electromagnetic interference (EMI) sensors. Temperature sensors monitor temperature changes around the electricity meter. Humidity sensors monitor changes in air humidity. EMI sensors monitor the strength and changes in electromagnetic fields. The selected sensors are installed near the electricity meter to ensure they accurately capture environmental conditions affecting meter performance. The sensor installation locations should represent the actual operating environment of the electricity meter. Sensors collect environmental data periodically or in real-time. The frequency of data collection depends on the type of sensor and the analytical needs. For temperature and humidity sensors, data is collected every few minutes to every few hours; while for EMI sensors, data is collected more frequently. The collected data is stored in a database or data lake, forming a sensor dataset.

[0033] S6: Input the sensor data set into the performance degradation model optimized according to the parameters to generate adaptive calibration results.

[0034] Specifically, the process involves removing any outliers or erroneous data, converting the data to a specific format, and normalizing or standardizing it. The dataset is split into training, validation, and test sets to evaluate the model's performance. The prepared sensor data set is then input into the performance degradation model. Model input typically includes time-series data and environmental factors related to meter performance, such as temperature, humidity, and electromagnetic interference. The model processes the input data to generate predictions of performance degradation. These predictions may include the meter's expected performance level at a specific future time point or the rate of performance degradation. Based on the model's predictions, adaptive calibration instructions or recommendations are generated. These results include calibration requirement indications, determining when meter calibration is needed. The calibration adjustment amount is calculated to compensate for performance degradation.

[0035] S7: Perform energy meter calibration management based on the adaptive calibration results.

[0036] Specifically, the adaptive calibration results are analyzed to determine whether the electricity meter requires calibration, and the urgency and importance of calibration. Based on the calibration results, a calibration plan is developed, including a calibration schedule, resource allocation, and workflow. Preferably, the equipment and personnel resources for performing the calibration are determined, and an appropriate calibration method is selected, such as remote calibration or on-site calibration, to minimize the impact of calibration on users' electricity consumption, such as selecting calibration during off-peak hours. The electricity meter calibration is performed according to the calibration plan. This includes sending calibration commands to the electricity meter via a remote communication system or dispatching technicians to the site for calibration. Detailed calibration information is recorded, including the calibration date, calibration personnel, and calibration results.

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

[0038] A temperature abnormality threshold is established based on the device information; a temperature influence function is constructed using the temperature abnormality threshold, as follows: Where b(T) is the temperature effect function, T c β is the temperature dysregulation threshold. T1 β is the first adaptive adjustment coefficient. T2 δ is the second adaptive adjustment coefficient. T The constant is used for adjustment; a performance degradation model is constructed based on the temperature effect function.

[0039] Specifically, the temperature degradation threshold refers to the critical value at which a temperature exceeding the normal operating range causes abnormal performance of the electricity meter. This threshold can be determined based on historical performance data and field test results. Analyze historical temperature data and corresponding electricity meter performance data to identify temperature points where performance significantly degrades, referring to temperature impact guidelines provided by the electricity meter manufacturer. Conduct field tests to determine the changes in electricity meter performance at specific temperatures. The temperature impact function describes the specific impact of temperature changes on electricity meter performance. Use statistical methods or machine learning algorithms to determine the parameters in the function, such as adaptive adjustment coefficients and adjustment constants. Validate 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 allows for more accurate prediction of the impact of temperature changes on electricity meter performance. Use the temperature impact function as a component of the performance degradation model. Train the model using historical data and evaluate its accuracy using a validation dataset.

[0040] Furthermore, the present invention also includes:

[0041] The electromagnetic interference effect function is constructed as follows:

[0042] Where d(E) is the electromagnetic interference effect function, β E γ is a logarithmic coefficient, characterizing the impact of electromagnetic interference on performance in the first stage. E The growth rate parameter is a logarithmic function, characterizing the sensitivity to performance degradation as electromagnetic interference increases. δ E σ is the pre-index coefficient used to characterize the impact of electromagnetic interference on performance in the second stage. E E is the adjustment parameter for the exponential decay rate, and E represents the electromagnetic interference intensity. A performance decay model is constructed using the electromagnetic interference influence function and the temperature influence function.

[0043] Specifically, electromagnetic interference (EMI) data of the environment in which the electricity meter is located is collected, including the intensity and frequency of the electromagnetic field. Simultaneously, the performance data of the electricity meter under different EMI conditions is recorded, and the relationship between EMI intensity and electricity meter performance is analyzed. Statistical methods or machine learning algorithms are used to determine the parameters in the EMI influence function, such as the logarithmic coefficient, growth rate parameter, pre-factor, and attenuation rate adjustment parameter. The EMI influence function is combined with the previously constructed temperature influence function to build a more comprehensive performance degradation model. This model will simultaneously consider the impact of temperature and EMI on electricity meter performance. Real-world data is used to verify the model's accuracy, and the model parameters are adjusted based on the verification results to improve the model's predictive ability.

[0044] Furthermore, the present invention also includes:

[0045] The calibration dataset of the electricity meter is recorded, and the calibration dataset stores adaptive calibration results in a time sequence; an adaptive calibration scale evaluation is performed based on the calibration dataset, and a supervised test cycle is constructed based on the evaluation results, the supervised test cycle being marked with a test frequency; the calibration verification of the electricity meter is performed through the supervised test cycle, and calibration feedback is generated; the performance degradation model is optimized based on the calibration feedback.

[0046] Specifically, the calibration dataset contains detailed information for each calibration, including the calibration date, calibration results, calibration equipment used, and the technicians performing the calibration. Ensure the calibration dataset can be stored chronologically, using a database or data management system to store and manage the calibration data. Adaptive calibration scalar evaluation is a quantitative assessment of the effectiveness of electricity meter calibration, helping to determine calibration frequency and strategies. Define evaluation criteria, such as post-calibration accuracy and stability. Analyze the calibration dataset to evaluate the effectiveness of each calibration. The supervised testing cycle is a period of testing and verification of electricity meters within a specified timeframe to ensure they continuously meet performance requirements. Determine the frequency of supervised testing based on the adaptive calibration scalar evaluation results. Plan a supervised testing schedule, including routine testing, periodic testing, and special testing. Calibration verification involves actual testing of the electricity meters through the supervised testing cycle to verify the calibration effectiveness. Perform performance testing of the electricity meters according to the supervised testing cycle. Record test results, including test data, test conditions, and test personnel. Generate calibration feedback based on the test results, including calibration effectiveness, existing problems, and suggested improvement measures. Optimize the performance degradation model based on the calibration feedback to improve its predictive accuracy and adaptability. The model parameters are adjusted based on calibration feedback, and new calibration data is integrated into the model for future training and prediction. Machine learning techniques are used to allow the model to learn from new data and continuously optimize its performance.

[0047] Furthermore, the present invention also includes:

[0048] An environmental anomaly cumulative early warning threshold is constructed based on the device information; cumulative environmental anomalies are calculated using the sensor data set; anomaly trigger determination is made based on the cumulative anomaly calculation result using the environmental anomaly cumulative early warning threshold; if the anomaly trigger determination result is a trigger result, an electricity meter anomaly early warning is generated, and electricity meter maintenance and management are performed based on the electricity meter anomaly early warning.

[0049] Specifically, the cumulative environmental anomaly warning threshold refers to the warning standard that triggers an abnormality in electricity meter performance when the cumulative impact of environmental factors, such as temperature, humidity, and electromagnetic interference, exceeds a certain limit. Historical environmental data and electricity meter performance data are analyzed to determine the cumulative impact of environmental factors on electricity meter performance. Warning thresholds are set by those skilled in the art and dynamically adjusted based on actual operating conditions. The cumulative anomalies of environmental factors are calculated by analyzing the sensor data set to assess their potential impact on electricity meter performance. Sensor data is cleaned and processed to ensure data quality and consistency. Statistical methods or machine learning algorithms are used to assess the cumulative impact of environmental factors. The cumulative anomaly calculation results are compared with the warning threshold to determine if an anomaly has been triggered. A judgment logic is set, such as triggering an anomaly warning when the cumulative anomaly exceeds the threshold. If the anomaly trigger judgment result is triggered, an electricity meter anomaly warning is generated. A warning message is generated, including the electricity meter identifier, anomaly description, and suggested actions. The maintenance team is promptly notified via SMS, email, or the maintenance system. Maintenance management of the electricity meter is carried out based on the electricity meter anomaly warning. Based on the early warning information, formulate a maintenance plan. Dispatch technical personnel to conduct on-site inspections and perform necessary maintenance operations.

[0050] Furthermore, the present invention also includes:

[0051] If the abnormal trigger determination result is no trigger result, then environmental abnormal features are established based on the cumulative abnormal calculation results; abnormal cumulative analysis is performed through the environmental abnormal features to generate cumulative abnormal constraints; the performance degradation model after parameter optimization is optimized based on the cumulative abnormal constraints, and the adaptive calibration result is updated according to the optimization compensation result.

[0052] Specifically, even if an anomaly is not triggered, environmental anomaly characteristics are still established based on the cumulative anomaly calculation results to track the changing trends of environmental factors. Key features, such as the fluctuation range and rate of change of environmental factors, are extracted from the cumulative anomaly calculation results and represented as numerical values ​​or vectors that can be used for subsequent analysis. Anomaly cumulative analysis is performed using these environmental anomaly characteristics to generate cumulative anomaly constraints to predict potential future environmental anomalies. Statistical methods or machine learning algorithms are used to build a predictive model to predict the cumulative anomaly trend of environmental factors. Based on the prediction results, the constraints on cumulative anomalies are determined, i.e., under what conditions the cumulative impact of environmental factors may exceed the warning threshold. Based on the cumulative anomaly constraints, the performance degradation model after parameter optimization is optimized and compensated to improve the model's adaptability to environmental anomalies. Model parameters, such as adaptive adjustment coefficients and attenuation rate adjustment parameters, are adjusted according to the cumulative anomaly constraints. The adjusted model is validated using a new dataset to ensure its predictive accuracy. Based on the results of the optimized and compensated performance degradation model, the adaptive calibration results are updated to reflect the impact of environmental anomalies on the performance of the electricity meter. Based on the optimized compensation results, the adaptive calibration adjustment amount is calculated, and the adaptive calibration results are updated, including the calibration adjustment amount and calibration frequency.

[0053] Furthermore, the present invention also includes:

[0054] Set an adaptive maintenance cycle; if the adaptive calibration results are all normal calibration results, activate the adaptive maintenance command in the adaptive maintenance cycle; perform periodic maintenance of the energy meter through the adaptive maintenance command.

[0055] Specifically, the adaptive maintenance cycle is a dynamically set maintenance cycle based on the energy meter's performance degradation model and environmental monitoring data. The performance degradation model predicts the energy meter's maintenance needs. Environmental factors, such as temperature, humidity, and electromagnetic interference, are considered in relation to the maintenance cycle. The maintenance cycle is dynamically adjusted based on actual operating conditions and maintenance feedback. If the adaptive calibration results are all normal calibration results, meaning the energy meter's performance is within acceptable limits, adaptive maintenance instructions are activated within the adaptive maintenance cycle. The latest adaptive calibration result data is collected, including the energy meter's performance parameters and environmental data. Data analysis tools, such as Excel and Python, are used to analyze the calibration results, comparing the energy meter's performance changes before and after calibration. Based on preset standards, the stability of the energy meter's performance is assessed, determining whether further calibration or maintenance is needed, and a calibration result analysis report is generated, including the analysis process, evaluation results, and recommendations. Based on the adaptive maintenance cycle prediction results, the current maintenance cycle to be performed for the energy meter is determined. Based on the energy meter's performance evaluation results, specific maintenance instructions are formulated, including maintenance content, maintenance personnel, and maintenance tools.

[0056] In summary, the adaptive calibration method for electricity meters provided by this invention has the following technical advantages:

[0057] By acquiring basic and supplementary data from the electricity meter, where the basic data is the meter's log data and the supplementary data includes an environmental dataset and known calibration data; performing time-series data alignment of the basic and supplementary data, dividing the environmental dataset into periods, and segmenting the time-series data alignment result based on the period division result to generate a time-series segmentation result; acquiring the electricity meter's device information, performing feature key analysis within the period based on the device information, and establishing interference weight factors for each feature; constructing a performance degradation model, and optimizing the parameters within the performance degradation model using the time-series segmentation result, wherein the performance degradation model is as follows: Where P is the performance decay function, ωT(s), ωH(s), and ωE(s) are the weighting factors for temperature, humidity, and electromagnetic interference at time s, respectively, P0 is the initial performance level, e is the base of the natural logarithm, a is the time decay coefficient, t is the time variable representing the cumulative time from the start of performance decay, s is the integral variable representing any time point within the time interval from 0 to t, b(T(s)) represents the influence function of temperature T on performance at time s, c(H(s)) represents the influence function of humidity H on performance at time s, and d(E(s)) represents the influence function of electromagnetic interference E on performance at time s. The system incorporates a function to assess the impact of electricity meter performance. It collects environmental data from monitoring sensors to construct a sensor dataset. This dataset is then input into a performance degradation model optimized based on parameters to generate adaptive calibration results. The adaptive calibration results are used for electricity meter calibration management. This effectively solves the technical problem in existing technologies where the inability to monitor electricity meter performance degradation in real time leads to delayed calibration, further affecting the accuracy of electricity metering. The system achieves effective calibration management of electricity meters, ensuring their long-term accuracy and reliability, and improving the efficiency of calibration work.

[0058] Example 2

[0059] Based on the adaptive calibration method for electricity meters described in the foregoing embodiments, and using the same inventive concept, this invention also provides an adaptive calibration system for electricity meters. Referring to Figure 2, the system includes:

[0060] The data acquisition module 11 is used to acquire basic data and supplementary data of the electricity meter. The basic data is the log data of the electricity meter, and the supplementary data includes environmental datasets and known calibration data.

[0061] The temporal segmentation result generation module 12 is used to perform temporal data alignment of the basic data and the supplementary data, perform periodic division of the environmental dataset, segment the temporal data alignment result according to the periodic division result, and generate temporal segmentation result.

[0062] Feature key analysis module 13 is used to acquire the device information of the electricity meter, perform feature key analysis on the time-series segmentation result within the period based on the device information, and establish interference weight factors for each feature.

[0063] Model building module 14 is used to build a performance degradation model and optimize the parameters within the performance degradation model using the time-series segmentation results. The performance degradation model is as follows:

[0064] Where P is the performance decay function, ωT(s), ωH(s), and ωE(s) are the interference weighting factors of temperature, humidity, and electromagnetic interference at time s, respectively, P0 is the initial performance level, e is the base of the natural logarithm, a is the time decay coefficient, t is the time variable, representing the cumulative time from the start of performance decay, s is the integral variable, representing any time point within the time interval from 0 to t, b(T(s)) represents the influence function of temperature T on performance at time s, c(H(s)) represents the influence function of humidity H on performance at time s, and d(E(s)) represents the influence function of electromagnetic interference E on performance at time s.

[0065] The sensor data set construction module 15 is used to collect environmental data of the electricity meter by monitoring sensors and construct a sensor data set.

[0066] An adaptive calibration result generation module 16 is used to input the sensing data set into a performance degradation model optimized according to parameters, and generate an adaptive calibration result.

[0067] The calibration management module 17 is used to manage the calibration of the electricity meter based on the adaptive calibration results.

[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; a temperature influence function is constructed using the temperature abnormality threshold, as follows: Where b(T) is the temperature effect function, T c β is the temperature dysregulation threshold. T1 β is the first adaptive adjustment coefficient. T2 δ is the second adaptive adjustment coefficient.T The constant is used for adjustment; a performance degradation model is constructed based on the temperature effect function.

[0070] Furthermore, the system also includes an interference effect function construction module, which is used to:

[0071] Construct the electromagnetic interference effect function as follows: Where d(E) is the electromagnetic interference effect function, β E γ is a logarithmic coefficient, characterizing the impact of electromagnetic interference on performance in the first stage. E The growth rate parameter is a logarithmic function, characterizing the sensitivity to performance degradation as electromagnetic interference increases. δ E σ is the pre-index coefficient used to characterize the impact of electromagnetic interference on performance in the second stage. E E is the adjustment parameter for the exponential decay rate, and E represents the electromagnetic interference intensity. A performance decay model is constructed using the electromagnetic interference influence function and the temperature influence function.

[0072] Furthermore, the system also includes a model optimization module, which is used for:

[0073] The calibration dataset of the electricity meter is recorded, and the calibration dataset stores adaptive calibration results in a time sequence; an adaptive calibration scale evaluation is performed based on the calibration dataset, and a supervised test cycle is constructed based on the evaluation results, the supervised test cycle being marked with a test frequency; the calibration verification of the electricity meter is performed through the supervised test cycle, and calibration feedback is generated; the performance degradation model is optimized based on the calibration feedback.

[0074] Furthermore, the system also includes a maintenance management module, which is used for:

[0075] An environmental anomaly cumulative early warning threshold is constructed based on the device information; cumulative environmental anomalies are calculated using the sensor data set; anomaly trigger determination is made based on the cumulative anomaly calculation result using the environmental anomaly cumulative early warning threshold; if the anomaly trigger determination result is a trigger result, an electricity meter anomaly early warning is generated, and electricity meter maintenance and management are performed based on the electricity meter anomaly early warning.

[0076] Furthermore, the system also includes a calibration result update module, which is used for:

[0077] If the abnormal trigger determination result is no trigger result, then environmental abnormal features are established based on the cumulative abnormal calculation results; abnormal cumulative analysis is performed through the environmental abnormal features to generate cumulative abnormal constraints; the performance degradation model after parameter optimization is optimized based on the cumulative abnormal constraints, and the adaptive calibration result is updated according to the optimization compensation result.

[0078] Furthermore, the system also includes a periodic maintenance module, which is used for:

[0079] Set an adaptive maintenance cycle; if the adaptive calibration results are all normal calibration results, activate the adaptive maintenance command in the adaptive maintenance cycle; perform periodic maintenance of the energy meter through the adaptive maintenance command.

[0080] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. The adaptive calibration method and specific examples of an energy meter in Embodiment 1 of Figure 1 are also applicable to the adaptive calibration system of an energy meter in this embodiment. Through the foregoing detailed description of the adaptive calibration method of an energy meter, those skilled in the art can clearly understand the adaptive calibration system of an energy meter in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here. As for the system disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and relevant parts can be referred to in the method section.

[0081] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily 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 invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0082] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of this invention and its equivalents, this invention also intends to include these modifications and variations.

Claims

1. An adaptive calibration method for an electricity meter, characterized in that, The method includes: Acquire basic and supplementary data from the electricity meter. The basic data is the electricity meter's log data, and the supplementary data includes environmental datasets and known calibration data. Perform time-series data alignment of the basic data and the supplementary data, and periodically divide the environmental dataset. Based on the periodic division result, segment the time-series data alignment result to generate a time-series segmentation result. Obtain the device information of the electricity meter, perform feature key analysis within the period based on the device information, and establish interference weight factors for each feature; A performance degradation model is constructed, and the parameters within the performance degradation model are optimized using the time-series segmentation results. The performance degradation model is as follows: Where P is the performance decay function, ωT(s), ωH(s), and ωE(s) are the interference weighting factors of temperature, humidity, and electromagnetic interference at time s, respectively, P0 is the initial performance level, e is the base of the natural logarithm, a is the time decay coefficient, t is the time variable, representing the cumulative time from the start of performance decay, s is the integral variable, representing any time point within the time interval from 0 to t, b(T(s)) represents the influence function of temperature T on performance at time s, c(H(s)) represents the influence function of humidity H on performance at time s, and d(E(s)) represents the influence function of electromagnetic interference E on performance at time s; By monitoring sensors, environmental data of electricity meters are collected to construct a sensor data set. The sensor data set is input into a performance degradation model optimized according to parameters to generate adaptive calibration results; The adaptive calibration results are used for electricity meter calibration management.

2. The method as described in claim 1, characterized in that, The construction of the performance degradation model also includes: A temperature abnormality threshold is established based on the aforementioned equipment information; The temperature effect function is constructed based on the temperature aberration threshold, as follows: Where b(T) is the temperature effect function, T c β is the temperature dysregulation threshold. T1 β is the first adaptive adjustment coefficient. T2 δ is the second adaptive adjustment coefficient. T This is the adjustment constant; A performance degradation model is constructed based on the temperature effect function.

3. The method as described in claim 2, characterized in that, The step of constructing the performance degradation model based on the temperature effect function further includes: The electromagnetic interference effect function is constructed as follows: Where d(E) is the electromagnetic interference effect function, β E γ is a logarithmic coefficient, characterizing the impact of electromagnetic interference on performance in the first stage. E The growth rate parameter is a logarithmic function, characterizing the sensitivity to performance degradation as electromagnetic interference increases. δ E σ is the pre-index coefficient used to characterize the impact of electromagnetic interference on performance in the second stage. E E is the adjustment parameter for the exponential decay rate, and E characterizes the electromagnetic interference intensity. A performance degradation model is constructed using the electromagnetic interference effect function and the temperature effect function.

4. The method as described in claim 1, characterized in that, The method further includes: Record the calibration dataset of the electricity meter, wherein the calibration dataset stores adaptive calibration results in a time sequence; An adaptive calibration scale evaluation is performed based on the calibration dataset, and a supervised test cycle is constructed based on the evaluation results. The supervised test cycle is marked with a test frequency. The electricity meter is calibrated and verified through the aforementioned supervised testing cycle, and calibration feedback is generated. The performance degradation model is optimized based on the calibration feedback.

5. The method as described in claim 1, characterized in that, The method further includes: Based on the device information, a cumulative early warning threshold for environmental anomalies is constructed; The cumulative anomaly calculation of the environment is performed using the aforementioned sensor data set; The cumulative anomaly calculation result is used to determine anomaly triggers by using the aforementioned cumulative environmental anomaly warning threshold. If the abnormal trigger determination result is a trigger result, an energy meter abnormality warning is generated, and energy meter maintenance and management are carried out based on the energy meter abnormality warning.

6. The method as described in claim 5, characterized in that, The step of determining the abnormality trigger based on the cumulative abnormality calculation result using the cumulative environmental abnormality early warning threshold also includes: If the abnormal trigger determination result is no trigger result, then environmental abnormality characteristics are established based on the cumulative abnormality calculation result; Anomaly accumulation analysis is performed based on the aforementioned environmental anomaly characteristics to generate cumulative anomaly constraints; The performance degradation model is optimized and compensated based on the cumulative anomaly constraints, and the adaptive calibration results are updated according to the optimization compensation results.

7. The method as described in claim 1, characterized in that, The method further includes: Set an adaptive maintenance cycle; If all the adaptive calibration results are normal calibration results, then the adaptive maintenance command is activated in the adaptive maintenance cycle. Periodic maintenance of the energy meter is performed using the adaptive maintenance instructions.

8. An adaptive calibration system for an electricity meter, characterized in that, The system comprises: steps for implementing the method according to any one of claims 1 to 7, wherein the system includes: The data acquisition module is used to acquire basic data and supplementary data of the electricity meter. The basic data is the log data of the electricity meter, and the supplementary data includes environmental datasets and known calibration data. A time-series segmentation result generation module is used to perform time-series data alignment of the basic data and the supplementary data, and to perform periodic division of the environmental dataset, and to segment the time-series data alignment result according to the periodic division result to generate a time-series segmentation result. The feature key analysis module is used to acquire the device information of the electricity meter, perform feature key analysis on the time-series segmentation result within the period based on the device information, and establish interference weight factors for each feature. A model building module is used to construct a performance degradation model and optimize the parameters within the performance degradation model based on the time-series segmentation results. The performance degradation model is as follows: Where P is the performance decay function, ωT(s), ωH(s), and ωE(s) are the interference weighting factors of temperature, humidity, and electromagnetic interference at time s, respectively, P0 is the initial performance level, e is the base of the natural logarithm, a is the time decay coefficient, t is the time variable, representing the cumulative time from the start of performance decay, s is the integral variable, representing any time point within the time interval from 0 to t, b(T(s)) represents the influence function of temperature T on performance at time s, c(H(s)) represents the influence function of humidity H on performance at time s, and d(E(s)) represents the influence function of electromagnetic interference E on performance at time s; A sensor data set construction module is used to collect environmental data of the electricity meter by monitoring sensors and construct a sensor data set. An adaptive calibration result generation module is used to input the sensor data set into a performance degradation model optimized according to parameters, and generate adaptive calibration results. A calibration management module is used to manage the calibration of the electricity meter based on the adaptive calibration results.

Images