Electric energy meter calibration method and electric energy meter calibration platform

Abstract

The invention discloses an electric energy meter calibration method and a meter calibration platform, and relates to the technical field of electric variable measurement, and the method comprises the steps: obtaining a plurality of historical operation data sets of a preset historical window through obtaining an electric energy meter set of a target meter calibration batch; the method comprises the following steps: acquiring a plurality of historical environment monitoring data sets, performing similar aggregation according to a preset working condition, acquiring a plurality of historical operation data sets under different working conditions, performing centralized analysis on the historical operation data sets and corresponding rated historical operation data under different working conditions, and acquiring error coefficients under different working conditions. And performing environment influence analysis on the plurality of historical environment monitoring data sets to obtain a plurality of environment interference coefficients. And performing meter calibration parameter identification to obtain a plurality of meter calibration parameters, and performing meter calibration on the electric energy meter set according to the plurality of meter calibration parameters. The technical problems that in the prior art, an electric energy meter calibration method is low in intelligence and low in meter calibration efficiency, and an electric energy meter cannot be accurately adjusted under various complex environments and working conditions are solved.

Description

Technical Field

[0001] The present application relates to the technical field related to measuring electrical variables, and in particular to an electric energy meter calibration method and a calibration platform. Background Art

[0002] The electric energy meter is a core device for measuring electricity consumption, and its measurement accuracy is of great significance to electricity billing and electricity management. However, during the long-term operation of the electric energy meter, due to the influence of environmental factors such as temperature, humidity, vibration, etc. and working conditions such as load changes, its measurement results may produce errors, which in turn affects the accuracy and reliability of measurement. The existing electric energy meter calibration methods usually rely on manual testing or simple correction methods based on fixed algorithms. The calibration efficiency is low and cannot meet the needs of large-scale calibration. On the other hand, fixed algorithms are difficult to fully consider complex operating environments and working conditions, resulting in poor adaptability of calibration results.

[0003] Therefore, in the prior art, the electric energy meter calibration method has low intelligence, low calibration efficiency, and technical problems such as being unable to accurately adjust the electric energy meter under a variety of complex environments and working conditions. Summary of the invention

[0004] This application provides an electric energy meter calibration method and calibration platform, which solves the technical problems of low intelligence, low calibration efficiency, and inability to accurately adjust the electric energy meter in a variety of complex environments and working conditions in the existing electric energy meter calibration method. It improves the metering accuracy and operating reliability of the electric energy meter, and significantly improves the calibration efficiency, meeting the technical effect of large-scale electric energy meter calibration needs.

[0005] The present application provides a method for calibrating an electric energy meter, the method comprising: obtaining an electric energy meter set of a target calibration batch, traversing multiple historical operation data sets of the electric energy meter set in a preset historical window, wherein each electric energy meter corresponds to a historical operation data set. Extracting the monitoring data of the sensor arranged at each electric energy meter in the preset historical window, and obtaining multiple historical environmental monitoring data sets. The multiple historical operation data sets are aggregated in the same category according to preset working conditions to obtain multiple clustered full-load historical operation data sets, multiple clustered light-load historical operation data sets, and multiple clustered no-load historical operation data sets. Traversing the multiple clustered full-load historical operation data sets, multiple clustered light-load historical operation data sets, and multiple clustered no-load historical operation data sets, and performing centralized analysis with multiple rated full-load operation data, multiple rated light-load historical operation data, and multiple rated no-load historical operation data to obtain multiple full-load error coefficients, multiple light-load error coefficients, and multiple no-load error coefficients. Traversing the multiple historical environmental monitoring data sets to perform environmental impact analysis, and obtain multiple environmental interference coefficients. Calibration parameters are identified based on the multiple full-load error coefficients, multiple light-load error coefficients, multiple no-load error coefficients and multiple environmental interference coefficients to obtain multiple calibration parameters, and the electric energy meter set is calibrated according to the multiple calibration parameters.

[0006] In the implementation method, the multiple clustered full-load historical operation data sets, the multiple clustered light-load historical operation data sets, and the multiple clustered no-load historical operation data sets are traversed, and centralized analysis is performed with multiple rated full-load operation data, multiple rated light-load historical operation data, and multiple rated no-load historical operation data to obtain multiple full-load error coefficients, multiple light-load error coefficients, and multiple no-load error coefficients, including: traversing the multiple clustered full-load historical operation data sets, the multiple clustered light-load historical operation data sets, and the multiple clustered no-load historical operation data sets, mapping error calculation is performed with multiple rated full-load operation data, multiple rated light-load historical operation data, and multiple rated no-load historical operation data to obtain multiple clustered full-load error sets, multiple clustered light-load error sets, and multiple clustered no-load error sets. The multiple clustered full-load error sets, multiple clustered light-load error sets, and multiple clustered no-load error sets are respectively compared with the corresponding multiple rated full-load operation data, multiple rated light-load historical operation data, and multiple rated no-load historical operation data to obtain multiple clustered full-load error coefficient sets, multiple clustered light-load error coefficient sets, and multiple clustered no-load error coefficient sets. The multiple clustered full-load error coefficient sets, multiple clustered light-load error coefficient sets, and multiple clustered no-load error coefficient sets are traversed and analyzed collectively to determine the multiple full-load error coefficients, multiple light-load error coefficients, and multiple no-load error coefficients.

[0007] In the implementation method, the means of multiple clustered full-load error coefficient sets, multiple clustered light-load error coefficient sets, and multiple clustered no-load error coefficient sets are calculated respectively to obtain multiple clustered full-load error coefficient means, multiple clustered light-load error coefficient means, and multiple clustered no-load error coefficient means. Taking the means of the multiple clustered full-load error coefficients as multiple full-load starting center points, the multiple clustered full-load error coefficient sets are respectively analyzed centrally to determine multiple full-load error coefficients. Taking the means of the multiple clustered light-load error coefficients as multiple light-load starting center points, the multiple clustered light-load error coefficient sets are respectively analyzed centrally to determine multiple light-load error coefficients. Taking the means of the multiple clustered no-load error coefficients as multiple no-load starting center points, the multiple clustered no-load error coefficient sets are respectively analyzed centrally to determine multiple no-load error coefficients.

[0008] In an implementation, the multiple clustered full load error coefficients are used as the multiple full load starting center points, and the multiple clustered full load error coefficient sets are respectively analyzed centrally to determine the multiple full load error coefficients, including: Obtain a center point iterative update formula, wherein the center point iterative update formula is: ; in, To fully update the center point, is the cluster full load error coefficient in the cluster full load error coefficient set, is the i-th cluster full load error coefficient in the cluster full load error coefficient set, is the full load starting center point, The weight kernel function is constructed based on the Gaussian function. The multiple full load starting center points of the multiple clustered full load error coefficient sets are updated using the center point iterative update formula until the preset update times are met, and the clustered full load error coefficients corresponding to the multiple full load update center points obtained in the last update are used as the multiple full load error coefficients.

[0009] In an implementation, traversing the multiple historical environmental monitoring data sets to perform environmental impact analysis and obtain multiple environmental interference coefficients includes: performing volatility identification on the multiple historical environmental monitoring data sets respectively to obtain multiple environmental fluctuation factors. Constructing multiple environmental monitoring change curves based on the multiple historical environmental monitoring data sets, and traversing and calculating multiple gradient change values ​​of the multiple environmental monitoring change curves. Using an environmental interference function to analyze the multiple environmental fluctuation factors and the multiple gradient change values ​​to obtain the multiple environmental interference coefficients.

[0010] In the implementation, the environmental interference function is constructed as follows: ; in, is a collection of historical environmental monitoring data. is the environmental interference coefficient, is the weight corresponding to the environmental fluctuation factor, is the weight corresponding to the gradient change value, , is the environmental fluctuation factor, is the gradient change value, Monitor the change curve for the environment.

[0011] In the implementation, calibration parameters are identified based on the multiple full-load error coefficients, multiple light-load error coefficients, multiple no-load error coefficients, and multiple environmental interference coefficients to obtain multiple calibration parameters, including: obtaining multiple sample full-load error coefficients, multiple sample light-load error coefficients, multiple sample no-load error coefficients, and multiple sample environmental interference coefficients, and corresponding multiple sample calibration parameters as training data sets. The training data sets are used to perform supervised training on the convolutional neural network, and the network parameters are updated during the training until the training converges to obtain a trained parameter identifier. The parameter identifier is used to identify the multiple full-load error coefficients, multiple light-load error coefficients, multiple no-load error coefficients, and multiple environmental interference coefficients to obtain the multiple calibration parameters.

[0012] The present application also provides an electric energy meter calibration platform, including: The data acquisition module is used to acquire a set of electric energy meters in a target calibration batch, and traverse a plurality of historical operation data sets of the electric energy meter set in a preset historical window, wherein each electric energy meter corresponds to a historical operation data set.

[0013] The environmental monitoring module is used to extract the monitoring data of the sensors arranged at each electric energy meter within the preset historical window to obtain multiple historical environmental monitoring data sets.

[0014] The operation data acquisition module is used to perform similar aggregation on the multiple historical operation data sets according to preset working conditions to obtain multiple clustered full-load historical operation data sets, multiple clustered light-load historical operation data sets and multiple clustered no-load historical operation data sets.

[0015] An error coefficient acquisition module is used to traverse the multiple clustered full-load historical operation data sets, the multiple clustered light-load historical operation data sets, and the multiple clustered no-load historical operation data sets, and perform centralized analysis with multiple rated full-load operation data, multiple rated light-load historical operation data, and multiple rated no-load historical operation data to obtain multiple full-load error coefficients, multiple light-load error coefficients, and multiple no-load error coefficients.

[0016] The interference coefficient acquisition module is used to traverse the multiple historical environmental monitoring data sets to perform environmental impact analysis and obtain multiple environmental interference coefficients.

[0017] The electric energy meter calibration module is used to identify calibration parameters based on the multiple full-load error coefficients, multiple light-load error coefficients, multiple no-load error coefficients and multiple environmental interference coefficients, obtain multiple calibration parameters, and calibrate the electric energy meter set according to the multiple calibration parameters.

[0018] The present application proposes a method and platform for calibrating electric energy meters, the method comprising: obtaining a set of electric energy meters of a target calibration batch, traversing multiple historical operation data sets of the electric energy meter set in a preset historical window, wherein each electric energy meter corresponds to a historical operation data set. Extracting the monitoring data of the sensor arranged at each electric energy meter in the preset historical window, and obtaining multiple historical environmental monitoring data sets. The multiple historical operation data sets are aggregated in the same category according to preset working conditions to obtain multiple clustered full-load historical operation data sets, multiple clustered light-load historical operation data sets, and multiple clustered no-load historical operation data sets. Traversing the multiple clustered full-load historical operation data sets, multiple clustered light-load historical operation data sets, and multiple clustered no-load historical operation data sets, and performing centralized analysis with multiple rated full-load operation data, multiple rated light-load historical operation data, and multiple rated no-load historical operation data, to obtain multiple full-load error coefficients, multiple light-load error coefficients, and multiple no-load error coefficients. Traversing the multiple historical environmental monitoring data sets to perform environmental impact analysis, and obtain multiple environmental interference coefficients. Based on the multiple full-load error coefficients, multiple light-load error coefficients, multiple no-load error coefficients and multiple environmental interference coefficients, calibration parameters are identified to obtain multiple calibration parameters, and the electric energy meter set is calibrated according to the multiple calibration parameters. The technical problems of low intelligence, low calibration efficiency and inability to accurately adjust the electric energy meter in a variety of complex environments and working conditions in the prior art are solved. The metering accuracy and operational reliability of the electric energy meter are improved, while the calibration efficiency is significantly improved, and the technical effect of meeting the calibration needs of large-scale electric energy meters is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure are briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the platform according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0020] Figure 1A schematic diagram of a flow chart of an electric energy meter calibration method provided in an embodiment of the present application.

[0021] Figure 2 A schematic diagram of the structure of an electric energy meter calibration platform provided in an embodiment of the present application.

[0022] Explanation of the reference numerals: data acquisition module 11 , environment monitoring module 12 , operation data acquisition module 13 , error coefficient acquisition module 14 , interference coefficient acquisition module 15 , electric energy meter calibration module 16 . DETAILED DESCRIPTION

[0023] 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 in accordance with the contents of the specification. 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 listed below.

[0024] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0025] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, platform, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0026] The present application embodiment provides an electric energy meter calibration method and a calibration platform, such as Figure 1 As shown, the method includes: Obtain a set of electric energy meters in a target calibration batch, and traverse multiple historical operation data sets of the electric energy meter set in a preset historical window, wherein each electric energy meter corresponds to a historical operation data set. Extract monitoring data of sensors deployed at each electric energy meter within the preset historical window to obtain multiple historical environmental monitoring data sets. Perform homogeneous aggregation on the multiple historical operation data sets according to preset working conditions to obtain multiple clustered full-load historical operation data sets, multiple clustered light-load historical operation data sets, and multiple clustered no-load historical operation data sets.

[0027] Obtain a set of electric energy meters of a target calibration batch, and traverse multiple historical operation data sets of the electric energy meter set in a preset historical window, wherein the historical operation data set includes data recorded during the operation process, such as current data, voltage data, power consumption data, and recording time. Among them, the electric energy meter set includes multiple electric energy meters in the same production batch that participate in the meter calibration operation. The target calibration batch is a production batch that requires electric energy meter calibration, and each electric energy meter corresponds to a historical operation data set. Subsequently, multiple historical environmental monitoring data sets within the preset historical window are obtained through the monitoring data of the sensors deployed at each electric energy meter within the preset historical window. The preset historical window is a pre-set collection time interval, such as extracting the collection data of the sensor in the past 1 day. The sensors include temperature sensors, humidity sensors, vibration sensors, and other sensors for collecting environmental parameters.

[0028] Furthermore, the multiple historical operation data sets are aggregated in the same category according to preset working conditions, and the operation parameters of the electric energy meter in a full-load environment, the operation parameters of the electric energy meter in a no-load environment, and the operation parameters of the electric energy meter in a light-load environment are respectively obtained from the multiple historical operation data sets, so as to obtain multiple clustered full-load historical operation data sets, multiple clustered light-load historical operation data sets, and multiple clustered no-load historical operation data sets. The full-load environment is an environment where the current is at the rated current, that is, the load-end current is 100% of the rated current, the light-load environment is an environment where the current is at the rated current, that is, the load-end current is 5%-10% of the rated current, and the no-load environment is an environment where the current can ensure that the electric energy meter starts correctly but does not record electric energy.

[0029] Traverse the multiple clustered full-load historical operation data sets, multiple clustered light-load historical operation data sets, and multiple clustered no-load historical operation data sets, and perform centralized analysis with multiple rated full-load operation data, multiple rated light-load historical operation data, and multiple rated no-load historical operation data to obtain multiple full-load error coefficients, multiple light-load error coefficients, and multiple no-load error coefficients. Traverse the multiple historical environmental monitoring data sets to perform environmental impact analysis to obtain multiple environmental interference coefficients. Perform calibration parameter identification based on the multiple full-load error coefficients, multiple light-load error coefficients, multiple no-load error coefficients, and multiple environmental interference coefficients to obtain multiple calibration parameters, and calibrate the electric energy meter set according to the multiple calibration parameters.

[0030] The data of the multiple clustered full-load historical operation data sets, the multiple clustered light-load historical operation data sets and the multiple clustered no-load historical operation data sets are traversed respectively, and a centralized analysis is performed with the multiple rated full-load operation data, the multiple rated light-load historical operation data and the multiple rated no-load historical operation data to obtain multiple full-load error coefficients, multiple light-load error coefficients and multiple no-load error coefficients. Further, the multiple historical environmental monitoring data sets are traversed to perform environmental impact analysis to obtain multiple environmental interference coefficients. After obtaining multiple environmental interference coefficients, calibration parameters are identified based on the multiple full-load error coefficients, multiple light-load error coefficients, multiple no-load error coefficients and multiple environmental interference coefficients input into a parameter identifier to obtain multiple calibration parameters output by the parameter identifier, each calibration parameter corresponds to an electric energy meter, and finally the electric energy meter set is calibrated according to the multiple calibration parameters. The technical problems of low intelligence, low calibration efficiency and inability to accurately adjust the electric energy meter in a variety of complex environments and working conditions in the prior art are solved. The metering accuracy and operational reliability of the electric energy meter are improved, while the calibration efficiency is significantly improved, achieving the technical effect of meeting the calibration needs of large-scale electric energy meters.

[0031] The method provided in the embodiment of the present application also includes: traversing the multiple clustered full-load historical operation data sets, multiple clustered light-load historical operation data sets, and multiple clustered no-load historical operation data sets, and performing mapping error calculation with multiple rated full-load operation data, multiple rated light-load historical operation data, and multiple rated no-load historical operation data, to obtain multiple clustered full-load error sets, multiple clustered light-load error sets, and multiple clustered no-load error sets. The multiple clustered full-load error sets, multiple clustered light-load error sets, and multiple clustered no-load error sets are respectively compared with the corresponding multiple rated full-load operation data, multiple rated light-load historical operation data, and multiple rated no-load historical operation data to obtain multiple clustered full-load error coefficient sets, multiple clustered light-load error coefficient sets, and multiple clustered no-load error coefficient sets. Traversing the multiple clustered full-load error coefficient sets, multiple clustered light-load error coefficient sets, and multiple clustered no-load error coefficient sets, respectively, and performing centralized analysis to determine the multiple full-load error coefficients, multiple light-load error coefficients, and the multiple no-load error coefficients.

[0032] Traversing the multiple clustered full-load historical operation data sets, multiple clustered light-load historical operation data sets, and multiple clustered no-load historical operation data sets, and performing centralized analysis with multiple rated full-load operation data, multiple rated light-load historical operation data, and multiple rated no-load historical operation data, to obtain multiple full-load error coefficients, multiple light-load error coefficients, and multiple no-load error coefficients, including: traversing the multiple clustered full-load historical operation data sets, multiple clustered light-load historical operation data sets, and multiple clustered no-load historical operation data sets, and performing mapping error calculation with multiple rated full-load operation data, multiple rated light-load historical operation data, and multiple rated no-load historical operation data, to obtain the difference between the historical full-load, light-load, and no-load operation data and the current data, voltage data, and other recorded data in the rated full-load, light-load, and no-load operation data. Thus, multiple clustered full-load error sets, multiple clustered light-load error sets, and multiple clustered no-load error sets are obtained. Among them, the rated full load, light load, and no-load operation data are standard operation record data without deviation recorded in the corresponding environment, and each operation record data has a corresponding error parameter. Further, the multiple clustered full load error sets, multiple clustered light load error sets, and multiple clustered no-load error sets are respectively compared with the corresponding multiple rated full load operation data, multiple rated light load historical operation data, and multiple rated no-load historical operation data to obtain multiple clustered full load error coefficient sets, multiple clustered light load error coefficient sets, and multiple clustered no-load error coefficient sets. The error coefficient sets are analyzed centrally to determine the multiple full load error coefficients, multiple light load error coefficients, and the multiple no-load error coefficients.

[0033] The method provided in the embodiment of the present application also includes: respectively calculating the means of multiple clustered full-load error coefficient sets, multiple clustered light-load error coefficient sets, and multiple clustered no-load error coefficient sets to obtain multiple clustered full-load error coefficient means, multiple clustered light-load error coefficient means, and multiple clustered no-load error coefficient means. Taking the means of the multiple clustered full-load error coefficients as multiple full-load starting center points, the multiple clustered full-load error coefficient sets are respectively analyzed centrally to determine multiple full-load error coefficients. Taking the means of the multiple clustered light-load error coefficients as multiple light-load starting center points, the multiple clustered light-load error coefficient sets are respectively analyzed centrally to determine multiple light-load error coefficients. Taking the means of the multiple clustered no-load error coefficients as multiple no-load starting center points, the multiple clustered no-load error coefficient sets are respectively analyzed centrally to determine multiple no-load error coefficients.

[0034] Calculate the means of multiple clustered full-load error coefficient sets, multiple clustered light-load error coefficient sets, and multiple clustered no-load error coefficient sets respectively, and obtain multiple clustered full-load error coefficient means, multiple clustered light-load error coefficient means, and multiple clustered no-load error coefficient means. Take the means of the multiple clustered full-load error coefficients as multiple full-load starting center points, and perform centralized analysis on the multiple clustered full-load error coefficient sets to determine multiple full-load error coefficients. Take the means of the multiple clustered light-load error coefficients as multiple light-load starting center points, and perform centralized analysis on the multiple clustered light-load error coefficient sets to determine multiple light-load error coefficients. Take the means of the multiple clustered no-load error coefficients as multiple no-load starting center points, and perform centralized analysis on the multiple clustered no-load error coefficient sets to determine multiple no-load error coefficients.

[0035] The method comprises: taking the mean values ​​of the multiple clustered full load error coefficients as multiple full load starting center points, performing centralized analysis on the multiple clustered full load error coefficient sets respectively, and determining multiple full load error coefficients, including: obtaining a center point iterative update formula, wherein the center point iterative update formula is: ; in, To fully update the center point, is the cluster full load error coefficient in the cluster full load error coefficient set, is the i-th cluster full load error coefficient in the cluster full load error coefficient set, is the full load starting center point, The weight kernel function is constructed based on the Gaussian function. The multiple full load starting center points of the multiple clustered full load error coefficient sets are updated using the center point iterative update formula until the preset update times are met, and the clustered full load error coefficients corresponding to the multiple full load update center points obtained in the last update are used as the multiple full load error coefficients.

[0036] The method provided by the embodiment of the present application also includes: performing volatility identification on the multiple historical environmental monitoring data sets respectively to obtain multiple environmental fluctuation factors. Constructing multiple environmental monitoring change curves based on the multiple historical environmental monitoring data sets, and traversing and calculating multiple gradient change values ​​of the multiple environmental monitoring change curves. Using the environmental interference function to analyze the multiple environmental fluctuation factors and the multiple gradient change values, to obtain the multiple environmental interference coefficients.

[0037] Traversing the multiple historical environmental monitoring data sets to perform environmental impact analysis and obtain multiple environmental interference coefficients, including: performing volatility identification on the multiple historical environmental monitoring data sets respectively, obtaining the variance calculation results of the historical environmental monitoring data sets, and obtaining multiple environmental fluctuation factors. Further, constructing multiple environmental monitoring change curves based on time series through the data in the multiple historical environmental monitoring data sets, and traversing and calculating multiple gradient change values ​​of the multiple environmental monitoring change curves, the gradient change value is the absolute value of the difference between the maximum and minimum values ​​of the environmental monitoring change curve. Finally, using the environmental interference function to analyze the multiple environmental fluctuation factors and the multiple gradient change values, the multiple environmental interference coefficients are obtained.

[0038] Among them, the environmental interference function is constructed as follows: ; in, is a collection of historical environmental monitoring data. is the environmental interference coefficient, is the weight corresponding to the environmental fluctuation factor, is the weight corresponding to the gradient change value, , is the environmental fluctuation factor, is the gradient change value, Monitor the change curve for the environment.

[0039] The method provided in the embodiment of the present application also includes: obtaining multiple sample full-load error coefficients, multiple sample light-load error coefficients, multiple sample no-load error coefficients, and multiple sample environmental interference coefficients, as well as corresponding multiple sample calibration parameters as training data sets. The convolutional neural network is supervised and trained using the training data sets, and the network parameters are updated during the training until the training converges, thereby obtaining a trained parameter identifier. The parameter identifier is used to identify the multiple full-load error coefficients, multiple light-load error coefficients, multiple no-load error coefficients, and multiple environmental interference coefficients, thereby obtaining the multiple calibration parameters.

[0040] Based on the multiple full-load error coefficients, multiple light-load error coefficients, multiple no-load error coefficients and multiple environmental interference coefficients, calibration parameters are identified to obtain multiple calibration parameters, including: obtaining multiple sample full-load error coefficients, multiple sample light-load error coefficients, multiple sample no-load error coefficients and multiple sample environmental interference coefficients, and corresponding multiple sample calibration parameters as training data sets, wherein the sample calibration parameters are key parameters used to adjust and optimize the measurement accuracy of the electric energy meter in specific electric energy meter correction parameters, such as offset correction parameters, proportional correction parameters, etc. The convolutional neural network is supervised and trained using the training data set, and the network parameters of the convolutional neural network are updated during the training until the model training converges and the sample calibration parameters finally output meet the preset accuracy, and a trained parameter identifier is obtained. Finally, the parameter identifier is used to identify the multiple full-load error coefficients, multiple light-load error coefficients, multiple no-load error coefficients and multiple environmental interference coefficients to obtain the multiple calibration parameters, each of which corresponds to an electric energy meter.

[0041] In the above, refer to Figure 1 A method for calibrating an electric energy meter according to an embodiment of the present invention is described in detail. Figure 2 An electric energy meter calibration platform according to an embodiment of the present invention is described.

[0042] An electric energy meter calibration platform according to an embodiment of the present invention solves the technical problems of low intelligence of electric energy meter calibration methods in the prior art, low calibration efficiency, and inability to accurately adjust the electric energy meter under a variety of complex environments and working conditions. The metering accuracy and operational reliability of the electric energy meter are improved, while the calibration efficiency is significantly improved, and the technical effect of meeting the calibration requirements of large-scale electric energy meters is achieved. An electric energy meter calibration platform includes: a data acquisition module 11, an environmental monitoring module 12, an operation data acquisition module 13, an error coefficient acquisition module 14, an interference coefficient acquisition module 15, and an electric energy meter calibration module 16.

[0043] The data acquisition module 11 is used to acquire a set of electric energy meters in a target calibration batch, and traverse a plurality of historical operation data sets of the electric energy meter set in a preset historical window, wherein each electric energy meter corresponds to a historical operation data set.

[0044] The environment monitoring module 12 is used to extract the monitoring data of the sensors arranged at each electric energy meter within the preset historical window to obtain multiple historical environment monitoring data sets.

[0045] The operation data acquisition module 13 is used to perform similar aggregation on the multiple historical operation data sets according to preset working conditions to obtain multiple clustered full-load historical operation data sets, multiple clustered light-load historical operation data sets and multiple clustered no-load historical operation data sets.

[0046] The error coefficient acquisition module 14 is used to traverse the multiple clustered full-load historical operation data sets, the multiple clustered light-load historical operation data sets, and the multiple clustered no-load historical operation data sets, and perform centralized analysis with the multiple rated full-load operation data, the multiple rated light-load historical operation data, and the multiple rated no-load historical operation data to obtain multiple full-load error coefficients, multiple light-load error coefficients, and multiple no-load error coefficients.

[0047] The interference coefficient acquisition module 15 is used to traverse the multiple historical environmental monitoring data sets to perform environmental impact analysis and obtain multiple environmental interference coefficients.

[0048] The electric energy meter calibration module 16 is used to identify calibration parameters based on the multiple full-load error coefficients, multiple light-load error coefficients, multiple no-load error coefficients and multiple environmental interference coefficients, obtain multiple calibration parameters, and calibrate the electric energy meter set according to the multiple calibration parameters.

[0049] The specific configuration of the error coefficient acquisition module 14 will be described in detail below. The error coefficient acquisition module 14 may further include: traversing the multiple clustered full-load historical operation data sets, the multiple clustered light-load historical operation data sets, and the multiple clustered no-load historical operation data sets, and performing centralized analysis with the multiple rated full-load operation data, the multiple rated light-load historical operation data, and the multiple rated no-load historical operation data, to obtain multiple full-load error coefficients, multiple light-load error coefficients, and multiple no-load error coefficients, including: traversing the multiple clustered full-load historical operation data sets, the multiple clustered light-load historical operation data sets, and the multiple clustered no-load historical operation data sets, and performing mapping error calculation with the multiple rated full-load operation data, the multiple rated light-load historical operation data, and the multiple rated no-load historical operation data, to obtain multiple clustered full-load error sets, multiple clustered light-load error sets, and multiple clustered no-load error sets. The multiple clustered full-load error sets, multiple clustered light-load error sets, and multiple clustered no-load error sets are respectively compared with the corresponding multiple rated full-load operation data, multiple rated light-load historical operation data, and multiple rated no-load historical operation data to obtain multiple clustered full-load error coefficient sets, multiple clustered light-load error coefficient sets, and multiple clustered no-load error coefficient sets. The multiple clustered full-load error coefficient sets, multiple clustered light-load error coefficient sets, and multiple clustered no-load error coefficient sets are traversed and analyzed collectively to determine the multiple full-load error coefficients, multiple light-load error coefficients, and multiple no-load error coefficients.

[0050] Below, the specific configuration of the error coefficient acquisition module 14 will continue to be described in detail. The error coefficient acquisition module 14 further includes: respectively calculating the means of multiple clustered full-load error coefficient sets, multiple clustered light-load error coefficient sets, and multiple clustered no-load error coefficient sets, and obtaining multiple clustered full-load error coefficient means, multiple clustered light-load error coefficient means, and multiple clustered no-load error coefficient means. Taking the means of the multiple clustered full-load error coefficients as multiple full-load starting center points, the multiple clustered full-load error coefficient sets are respectively analyzed centrally to determine multiple full-load error coefficients. Taking the means of the multiple clustered light-load error coefficients as multiple light-load starting center points, the multiple clustered light-load error coefficient sets are respectively analyzed centrally to determine multiple light-load error coefficients. Taking the means of the multiple clustered no-load error coefficients as multiple no-load starting center points, the multiple clustered no-load error coefficient sets are respectively analyzed centrally to determine multiple no-load error coefficients.

[0051] The specific configuration of the error coefficient acquisition module 14 will be described in detail below. The error coefficient acquisition module 14 may further include: using the mean of the multiple clustered full load error coefficients as multiple full load starting center points, performing centralized analysis on the multiple clustered full load error coefficient sets respectively, and determining multiple full load error coefficients, including: Obtain a center point iterative update formula, wherein the center point iterative update formula is: ; in, To fully update the center point, is the cluster full load error coefficient in the cluster full load error coefficient set, is the i-th cluster full load error coefficient in the cluster full load error coefficient set, is the full load starting center point, The weight kernel function is constructed based on the Gaussian function. The multiple full load starting center points of the multiple clustered full load error coefficient sets are updated using the center point iterative update formula until the preset update times are met, and the clustered full load error coefficients corresponding to the multiple full load update center points obtained in the last update are used as the multiple full load error coefficients.

[0052] The specific configuration of the interference coefficient acquisition module 15 will be described in detail below. The interference coefficient acquisition module 15 further includes: traversing the multiple historical environmental monitoring data sets to perform environmental impact analysis to obtain multiple environmental interference coefficients, including: performing volatility identification on the multiple historical environmental monitoring data sets respectively to obtain multiple environmental fluctuation factors. Construct multiple environmental monitoring change curves based on the multiple historical environmental monitoring data sets, and traverse and calculate multiple gradient change values ​​of the multiple environmental monitoring change curves. Use the environmental interference function to analyze the multiple environmental fluctuation factors and the multiple gradient change values ​​to obtain the multiple environmental interference coefficients.

[0053] The specific configuration of the interference coefficient acquisition module 15 will be described in detail below. The interference coefficient acquisition module 15 further includes: constructing an environmental interference function, which is constructed as follows: ; in, is a collection of historical environmental monitoring data. is the environmental interference coefficient, is the weight corresponding to the environmental fluctuation factor, is the weight corresponding to the gradient change value, , is the environmental fluctuation factor, is the gradient change value, Monitor the change curve for the environment.

[0054] The specific configuration of the electric energy meter calibration module 16 will be described in detail below. The electric energy meter calibration module 16 further includes: based on the multiple full-load error coefficients, multiple light-load error coefficients, multiple no-load error coefficients and multiple environmental interference coefficients, calibration parameters are identified to obtain multiple calibration parameters, including: obtaining multiple sample full-load error coefficients, multiple sample light-load error coefficients, multiple sample no-load error coefficients and multiple sample environmental interference coefficients, and corresponding multiple sample calibration parameters as training data sets. The convolutional neural network is supervised and trained using the training data set, and the network parameters are updated during the training until the training converges to obtain a trained parameter identifier. The parameter identifier is used to identify the multiple full-load error coefficients, multiple light-load error coefficients, multiple no-load error coefficients and multiple environmental interference coefficients to obtain the multiple calibration parameters.

[0055] An electric energy meter calibration platform provided in an embodiment of the present invention can execute an electric energy meter calibration method provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0056] Although the present application makes various references to certain modules in the platform according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or the server, and the various units and modules included are only divided according to functional logic, but are not limited to the above divisions, as long as the corresponding functions can be achieved. In addition, the specific names of the functional units are only for the convenience of distinguishing from each other and are not used to limit the scope of protection of the present invention.

[0057] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A method for calibrating an electric energy meter, characterized in that: The method comprises: Acquire a set of electric energy meters of a target calibration batch, and traverse a plurality of historical operation data sets of the electric energy meter set in a preset historical window, wherein each electric energy meter corresponds to one historical operation data set; Extracting monitoring data of sensors arranged at each electric energy meter within the preset historical window to obtain multiple historical environmental monitoring data sets; The multiple historical operation data sets are aggregated according to preset working conditions to obtain multiple clustered full-load historical operation data sets, multiple clustered light-load historical operation data sets, and multiple clustered no-load historical operation data sets; Traversing the multiple clustered full-load historical operation data sets, the multiple clustered light-load historical operation data sets, and the multiple clustered no-load historical operation data sets, and performing centralized analysis with the multiple rated full-load operation data, the multiple rated light-load historical operation data, and the multiple rated no-load historical operation data, to obtain multiple full-load error coefficients, multiple light-load error coefficients, and multiple no-load error coefficients; Traversing the plurality of historical environmental monitoring data sets to perform environmental impact analysis and obtain a plurality of environmental interference coefficients; Calibration parameters are identified based on the multiple full-load error coefficients, multiple light-load error coefficients, multiple no-load error coefficients and multiple environmental interference coefficients to obtain multiple calibration parameters, and the electric energy meter set is calibrated according to the multiple calibration parameters.

2. The method for calibrating an electric energy meter according to claim 1, characterized in that: Traversing the multiple clustered full-load historical operation data sets, the multiple clustered light-load historical operation data sets, and the multiple clustered no-load historical operation data sets, and centrally analyzing with the multiple rated full-load operation data, the multiple rated light-load historical operation data, and the multiple rated no-load historical operation data, to obtain multiple full-load error coefficients, multiple light-load error coefficients, and multiple no-load error coefficients, including: Traversing the multiple clustered full-load historical operation data sets, the multiple clustered light-load historical operation data sets, and the multiple clustered no-load historical operation data sets, and performing mapping error calculation with the multiple rated full-load operation data, the multiple rated light-load historical operation data, and the multiple rated no-load historical operation data, to obtain multiple clustered full-load error sets, multiple clustered light-load error sets, and multiple clustered no-load error sets; Respectively comparing the multiple clustered full-load error sets, the multiple clustered light-load error sets, and the multiple clustered no-load error sets with the corresponding multiple rated full-load operation data, the multiple rated light-load historical operation data, and the multiple rated no-load historical operation data to obtain multiple clustered full-load error coefficient sets, multiple clustered light-load error coefficient sets, and multiple clustered no-load error coefficient sets; The multiple clustered full-load error coefficient sets, the multiple clustered light-load error coefficient sets, and the multiple clustered no-load error coefficient sets are traversed and analyzed collectively to determine the multiple full-load error coefficients, the multiple light-load error coefficients, and the multiple no-load error coefficients.

3. A method for calibrating an electric energy meter as claimed in claim 2, characterized in that: include: Calculate the means of multiple clustered full-load error coefficient sets, multiple clustered light-load error coefficient sets, and multiple clustered no-load error coefficient sets respectively, and obtain the means of multiple clustered full-load error coefficients, the means of multiple clustered light-load error coefficients, and the means of multiple clustered no-load error coefficients; Taking the mean values ​​of the multiple clustered full load error coefficients as multiple full load starting center points, performing centralized analysis on the multiple clustered full load error coefficient sets respectively to determine multiple full load error coefficients; Taking the mean values ​​of the plurality of clustered light load error coefficients as the plurality of light load starting center points, performing centralized analysis on the plurality of clustered light load error coefficient sets respectively to determine a plurality of light load error coefficients; Taking the mean values ​​of the multiple clustered no-load error coefficients as multiple no-load starting center points, the multiple clustered no-load error coefficient sets are respectively analyzed collectively to determine multiple no-load error coefficients.

4. A method for calibrating an electric energy meter as claimed in claim 3, characterized in that: Taking the mean values ​​of the multiple clustered full load error coefficients as multiple full load starting center points, the multiple clustered full load error coefficient sets are respectively analyzed centrally to determine multiple full load error coefficients, including: Obtain a center point iterative update formula, wherein the center point iterative update formula is: ； in, To fully update the center point, is the cluster full load error coefficient in the cluster full load error coefficient set, is the i-th cluster full load error coefficient in the cluster full load error coefficient set, is the full load starting center point, is a weight kernel function built based on the Gaussian function; The multiple full load starting center points of the multiple clustered full load error coefficient sets are updated using the center point iterative update formula until the preset number of updates is met, and the clustered full load error coefficients corresponding to the multiple full load update center points obtained in the last update are used as the multiple full load error coefficients.

5. The method for calibrating an electric energy meter according to claim 1, characterized in that: The plurality of historical environmental monitoring data sets are traversed to perform environmental impact analysis to obtain a plurality of environmental interference coefficients, including: Performing volatility identification on the multiple historical environmental monitoring data sets respectively to obtain multiple environmental volatility factors; Constructing a plurality of environmental monitoring change curves according to the plurality of historical environmental monitoring data sets, and traversing and calculating a plurality of gradient change values ​​of the plurality of environmental monitoring change curves; The multiple environmental fluctuation factors and the multiple gradient change values ​​are analyzed using an environmental interference function to obtain the multiple environmental interference coefficients.

6. A method for calibrating an electric energy meter as claimed in claim 5, characterized in that: include: Construct the environment interference function as follows: ； in, is a collection of historical environmental monitoring data. is the environmental interference coefficient, is the weight corresponding to the environmental fluctuation factor, is the weight corresponding to the gradient change value, , is the environmental fluctuation factor, is the gradient change value, Monitor the change curve for the environment.

7. The method for calibrating an electric energy meter according to claim 1, characterized in that: Based on the multiple full-load error coefficients, the multiple light-load error coefficients, the multiple no-load error coefficients and the multiple environmental interference coefficients, calibration parameter identification is performed to obtain multiple calibration parameters, including: Obtaining multiple sample full-load error coefficients, multiple sample light-load error coefficients, multiple sample no-load error coefficients, and multiple sample environmental interference coefficients, as well as corresponding multiple sample calibration parameters as a training data set; The convolutional neural network is supervised and trained using the training data set, and the network parameters are updated during the training until the training converges to obtain a trained parameter identifier; The parameter identifier is used to identify the multiple full-load error coefficients, the multiple light-load error coefficients, the multiple no-load error coefficients and the multiple environmental interference coefficients to obtain the multiple calibration parameters.

8. An electric energy meter calibration platform, characterized in that: The platform includes: A data acquisition module, used to acquire a set of electric energy meters of a target calibration batch, and traverse a plurality of historical operation data sets of the electric energy meter set in a preset historical window, wherein each electric energy meter corresponds to one historical operation data set; An environmental monitoring module, used to extract monitoring data of sensors arranged at each electric energy meter within the preset historical window, and obtain multiple historical environmental monitoring data sets; An operation data acquisition module, used to perform similar aggregation on the multiple historical operation data sets according to preset working conditions, to obtain multiple clustered full-load historical operation data sets, multiple clustered light-load historical operation data sets, and multiple clustered no-load historical operation data sets; An error coefficient acquisition module is used to traverse the multiple clustered full-load historical operation data sets, the multiple clustered light-load historical operation data sets, and the multiple clustered no-load historical operation data sets, and perform centralized analysis with the multiple rated full-load operation data, the multiple rated light-load historical operation data, and the multiple rated no-load historical operation data to obtain multiple full-load error coefficients, multiple light-load error coefficients, and multiple no-load error coefficients; An interference coefficient acquisition module, used to traverse the plurality of historical environmental monitoring data sets to perform environmental impact analysis and obtain a plurality of environmental interference coefficients; The electric energy meter calibration module is used to identify calibration parameters based on the multiple full-load error coefficients, multiple light-load error coefficients, multiple no-load error coefficients and multiple environmental interference coefficients, obtain multiple calibration parameters, and calibrate the electric energy meter set according to the multiple calibration parameters.

Images